© 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. 164001
    Prev
    Next
    INDEX
    Explanations

    collocations and phrase completions

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

    range of numbers

    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
    spf
    0.50
    re
    0.50
    will
    0.49
    Salve
    0.48
    腚
    0.47
    args
    0.47
    ws
    0.47
    就會
    0.46
    ll
    0.46
    rq
    0.46
    POSITIVE LOGITS
     parenteral
    0.55
     profane
    0.55
     refractory
    0.53
     situé
    0.50
     سکے
    0.50
     đứng
    0.49
     destructive
    0.49
     һ
    0.49
     inom
    0.49
     matemat
    0.48
    Activations Density 0.000%

    No Known Activations