© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48509
    Prev
    Next
    INDEX
    Explanations

    cellForRowAt or toString

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    strncpy
    -0.80
     fielding
    -0.71
     BANG
    -0.70
    laid
    -0.68
    ᱖
    -0.68
    OWE
    -0.67
     personnaliser
    -0.67
    ithin
    -0.65
    हो
    -0.64
     logrado
    -0.64
    POSITIVE LOGITS
    哎呀
    0.77
     unlawful
    0.75
     Brewery
    0.72
    等我
    0.70
     longa
    0.70
     sırasında
    0.69
    呜呜
    0.69
    輝
    0.66
     coro
    0.66
    ataly
    0.65
    Activations Density 0.070%

    No Known Activations