© 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. 179180
    Prev
    Next
    INDEX
    Explanations

    conventional dressings

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

    lists and categories

    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
    g
    0.53
    a
    0.52
    dess
    0.44
     softness
    0.44
    ን
    0.43
    golf
    0.42
    عا
    0.42
     superficially
    0.42
    ه
    0.42
    澶
    0.42
    POSITIVE LOGITS
     Einrichtung
    0.48
     جميع
    0.47
    toare
    0.47
     demikian
    0.46
     poprzed
    0.45
     amacıyla
    0.44
     предыду
    0.44
     метою
    0.44
     vorhand
    0.43
     estavam
    0.43
    Activations Density 0.001%

    No Known Activations