© 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. 145732
    Prev
    Next
    INDEX
    Explanations

    actions or states followed by context

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

    logical disjunctions and multilingual indicators

    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
     seguenti
    0.50
     başladı
    0.48
     ši
    0.47
     sıra
    0.47
     ",")
    0.46
     remarquable
    0.46
     ។
    0.46
     salió
    0.45
     há
    0.44
     botched
    0.44
    POSITIVE LOGITS
    OR
    0.53
    Omega
    0.49
    or
    0.48
    冬
    0.48
     Enable
    0.46
     Omega
    0.45
     OR
    0.45
    심히
    0.45
    KEN
    0.43
     organismes
    0.43
    Activations Density 0.000%

    No Known Activations