© 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. 42385
    Prev
    Next
    INDEX
    Explanations

    referring to previously mentioned

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

    php code blocks

    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
    Sig
    0.40
     sticking
    0.39
    שו
    0.39
    prov
    0.39
    missible
    0.39
    ⵕ
    0.38
     podr
    0.38
    didn
    0.38
    trash
    0.38
    フォー
    0.38
    POSITIVE LOGITS
    :"))
    0.43
     n
    0.42
     మరి
    0.41
     জলা
    0.40
     ところ
    0.39
     ((
    0.38
     то
    0.37
    ================
    0.37
    ineri
    0.37
     Puoi
    0.37
    Activations Density 0.000%

    No Known Activations