© 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. 30640
    Prev
    Next
    INDEX
    Explanations

    identifying names and roles

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

    legal phrases and definitions

    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
    ಂಡ್
    0.45
    (
    0.45
     mout
    0.44
     bracket
    0.41
    ρι
    0.40
    adona
    0.40
    0.40
     runner
    0.40
     Igreja
    0.40
     bullet
    0.39
    POSITIVE LOGITS
    became
    0.40
    郃
    0.39
     હાલ
    0.39
    תו
    0.38
     निम्न
    0.38
     옳
    0.38
    NOWLEDGE
    0.38
     قوت
    0.38
    tableName
    0.38
     заве
    0.38
    Activations Density 0.000%

    No Known Activations