© 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. 57879
    Prev
    Next
    INDEX
    Explanations

    taxes, laws, or numbers followed by parenthesis

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

    lists, bullet points, or specific roles

    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
    Elis
    0.52
     방식으로
    0.44
    σης
    0.43
    售
    0.42
     Wert
    0.41
    த்திக்க
    0.41
    weaver
    0.40
    ъз
    0.39
     Kost
    0.39
    Preis
    0.39
    POSITIVE LOGITS
    覇
    0.44
     ย
    0.43
     那麼
    0.43
    밧
    0.43
     યુ
    0.42
    !!!!!!!
    0.41
     ब्राह्मण
    0.40
    を務
    0.40
    kite
    0.40
     ดิ
    0.40
    Activations Density 0.000%

    No Known Activations