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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86045
    Prev
    Next
    INDEX
    Explanations

    anthropomorphic, microbiological

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

    scientific terms related to biology, particularly microbiology and related disciplines.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    蹋
    -4.69
    CHREIB
    -3.78
    铼
    -3.69
    嚒
    -3.50
    沕
    -3.47
    ſſel
    -3.33
    ❘
    -3.28
    屃
    -3.22
    嗉
    -3.19
    öpfer
    -3.16
    POSITIVE LOGITS
    0
    5.66
     {
    4.44
    9
    4.41
    2
    4.38
    1
    4.19
    7
    4.09
    4
    3.92
    --
    3.89
    8
    3.86
    ---
    3.66
    Activations Density 0.036%

    No Known Activations