© 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. 17918
    Prev
    Next
    INDEX
    Explanations

    is $ or was $

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

    crosses below

    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
     миро
    0.46
    <unused2157>
    0.43
     meus
    0.42
     effectués
    0.42
    <unused323>
    0.42
     quotidienne
    0.40
     mixte
    0.40
    畕
    0.40
     indispensables
    0.40
     industriales
    0.40
    POSITIVE LOGITS
    binghamton
    0.46
    paran
    0.44
    perms
    0.43
    ipple
    0.42
    雍
    0.42
    perm
    0.42
    abstract
    0.42
    evidence
    0.41
    asal
    0.41
    adanam
    0.40
    Activations Density 0.001%

    No Known Activations