© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 64253
    Prev
    Next
    INDEX
    Explanations

    producing short, message to, potential for, surprising interest

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

    IELTS speaking prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .\
    0.54
     amén
    0.54
    exception
    0.52
    mat
    0.49
     .
    0.48
     amend
    0.48
     exception
    0.47
     mutex
    0.47
     for
    0.46
    typedef
    0.46
    POSITIVE LOGITS
     국민
    0.52
     পরিষদের
    0.50
     Öffentlichkeit
    0.48
    荅
    0.48
     அரசின்
    0.47
    Councillor
    0.46
     सांसद
    0.46
    墺
    0.45
     क्यो
    0.45
     பகுதியில்
    0.45
    Activations Density 0.000%

    No Known Activations