© 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. 148237
    Prev
    Next
    INDEX
    Explanations

    year access reconstruction negatively

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

    words separated by conjunctions

    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
    include
    0.47
    don
    0.45
    ia
    0.44
    sym
    0.44
    doi
    0.43
     cumbersome
    0.41
    tell
    0.41
    c
    0.41
    ortal
    0.40
    ospor
    0.40
    POSITIVE LOGITS
     молод
    0.47
     fraudsters
    0.46
     молодой
    0.44
     धोखाध
    0.43
     הייתה
    0.42
    StillWater
    0.42
    ❰
    0.42
     الوصول
    0.42
    ޭ
    0.41
     scammers
    0.41
    Activations Density 0.001%

    No Known Activations