© 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. 124654
    Prev
    Next
    INDEX
    Explanations

    acquisition, specified, if, any

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

    common grammatical continuations

    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
    Drawable
    0.48
    ㄉ
    0.46
    撲
    0.46
     نہيں
    0.45
     Umlauf
    0.45
    থা
    0.44
    纖
    0.44
    變
    0.42
    etum
    0.42
    分為
    0.41
    POSITIVE LOGITS
     pausing
    0.47
    낑
    0.47
     penalties
    0.47
     easements
    0.45
     trapped
    0.45
     revenues
    0.44
     covenants
    0.44
     calibrated
    0.44
     accomplishing
    0.44
     discounts
    0.43
    Activations Density 0.001%

    No Known Activations