© 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. 66981
    Prev
    Next
    INDEX
    Explanations

    activities, parents, situation, simple, rule, landscaping

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

    moving away, putting, find, cartoon

    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
     eux
    0.45
     zuverläss
    0.44
     brisket
    0.42
    入門
    0.41
     personnal
    0.40
     Flugh
    0.40
     henkil
    0.40
    氏
    0.40
     acier
    0.40
     Commencez
    0.40
    POSITIVE LOGITS
    Pdf
    0.45
    Subscriptions
    0.45
    Knife
    0.44
    scopes
    0.44
    嗕
    0.44
    टीवी
    0.44
     Arrangements
    0.44
    jene
    0.42
    יא
    0.42
    នឹង
    0.42
    Activations Density 0.006%

    No Known Activations