© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 125229
    Prev
    Next
    INDEX
    Explanations

    banned, provider, CBN

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

    financial and technical concepts

    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
     suger
    0.49
    말로
    0.46
     actin
    0.46
     moderate
    0.46
    嗜
    0.46
     năng
    0.44
    ,
    0.44
     brin
    0.44
     Nat
    0.42
     immunoglobulin
    0.42
    POSITIVE LOGITS
    eye
    0.52
     Präsident
    0.49
     zwei
    0.48
    readme
    0.46
    ienze
    0.45
     বললো
    0.45
    diary
    0.44
    粙
    0.43
     срока
    0.43
    irish
    0.43
    Activations Density 0.000%

    No Known Activations