© 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. 104749
    Prev
    Next
    INDEX
    Explanations

    non-english words

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

    connections and learning

    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
     favors
    0.47
    袒
    0.44
     favoring
    0.44
     \
    0.42
     defenseman
    0.42
     ав
    0.42
     choosing
    0.41
    auw
    0.41
     riconosc
    0.40
    igay
    0.40
    POSITIVE LOGITS
    럿
    0.53
    bild
    0.52
     somit
    0.50
     kredit
    0.49
     Verlust
    0.48
     Vermö
    0.48
    亥
    0.48
    نين
    0.48
     baat
    0.48
     Bugün
    0.47
    Activations Density 0.000%

    No Known Activations