© 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. 47362
    Prev
    Next
    INDEX
    Explanations

    specific nouns following articles

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

    bit quantization

    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
     Mold
    0.55
     Molding
    0.52
    ube
    0.49
    -
    0.49
    新型
    0.48
    agement
    0.48
     Mould
    0.47
     Endgame
    0.46
     Wyndham
    0.46
     Fulham
    0.46
    POSITIVE LOGITS
     cambios
    0.58
     errore
    0.50
    ٿ
    0.50
     zmian
    0.50
     آئے
    0.50
     cambiado
    0.49
    <unused22>
    0.49
     baixar
    0.48
     flung
    0.48
     ءَ
    0.48
    Activations Density 0.000%

    No Known Activations