© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 187224
    Prev
    Next
    INDEX
    Explanations

    our clients and experience

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

    existing purples, justifies injustice, revolves around

    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
    Negative Logits
     عمل
    0.52
    Rew
    0.46
    堀
    0.44
     پرو
    0.43
     بِ
    0.43
    ണ്യ
    0.43
    Silence
    0.43
    𝙇
    0.42
     પછી
    0.42
    Modules
    0.42
    POSITIVE LOGITS
     der
    0.49
    ;
    0.47
     expose
    0.46
     movimientos
    0.46
    ﯽ
    0.45
    die
    0.45
     exposição
    0.44
     this
    0.44
     epidermal
    0.44
     vd
    0.44
    Activations Density 0.000%

    No Known Activations