© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42754
    Prev
    Next
    INDEX
    Explanations

    rod-shaped or rod-like objects

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

    The neuron detects mentions of rod-shaped objects or structures, particularly in technical or scientific contexts.

    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
     treacherous
    -2.77
    jų
    -2.73
    昞
    -2.58
    臯
    -2.56
    晅
    -2.55
    呖
    -2.53
    聼
    -2.47
     thoughtful
    -2.44
     ruinas
    -2.41
     Houſe
    -2.34
    POSITIVE LOGITS
    翃
    2.98
     recogida
    2.53
     the
    2.53
     Any
    2.47
    ":
    2.47
    2
    2.47
    ";
    2.45
    .,
    2.45
     citing
    2.39
     afectada
    2.39
    Activations Density 0.008%

    No Known Activations