© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81534
    Prev
    Next
    INDEX
    Explanations

    mice / mouse strains

    np_acts-logits-general · gemini-2.5-flash-lite

    references to laboratory mouse strains, particularly BALB/c and C57BL/6 mice used in scientific experiments.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is highly responsive to numeric tokens and alphanumeric codes (e.g. digits, counts, and strain designations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     excelencia
    -0.79
    cplusplus
    -0.78
    overse
    -0.76
     GBP
    -0.73
    ikin
    -0.73
    兔
    -0.71
     رہ
    -0.71
    prehension
    -0.70
    Mall
    -0.70
    ორ
    -0.69
    POSITIVE LOGITS
     mouse
    4.34
     mice
    4.22
     Mouse
    3.31
     Mice
    3.30
    mouse
    3.28
     murine
    3.08
    Mice
    3.06
    Mouse
    2.98
    mice
    2.94
    MOUSE
    2.50
    Activations Density 0.280%

    No Known Activations