© 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. 15246
    Prev
    Next
    INDEX
    Explanations

    Valentines collaboration

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

    topics following colons

    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
     ሲ
    0.61
     ヴィンテージ
    0.56
     भत्ता
    0.53
     Warrington
    0.52
    კო
    0.50
     より
    0.49
     ነገር
    0.47
     ነው
    0.47
     നാല
    0.47
    تال
    0.46
    POSITIVE LOGITS
    ernes
    0.49
    界的
    0.48
     Lemmas
    0.46
    imilar
    0.44
    diği
    0.44
    \
    0.43
    是因为
    0.42
     isotopic
    0.42
     schemas
    0.42
    د
    0.42
    Activations Density 0.000%

    No Known Activations