© 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. 132979
    Prev
    Next
    INDEX
    Explanations

    collocations of words

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

    specific inquiry and tone

    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
     dan
    0.54
    P
    0.53
     пора
    0.52
     spell
    0.49
     oc
    0.46
    0.45
     P
    0.44
     hết
    0.44
     presumably
    0.43
     περί
    0.43
    POSITIVE LOGITS
    اویز
    0.49
    تمد
    0.47
    employment
    0.45
    ಿಗ
    0.45
    
    0.45
    цька
    0.44
    GoAbroad
    0.44
    inie
    0.44
    '%
    0.43
    ină
    0.43
    Activations Density 0.001%

    No Known Activations