© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3143
    Prev
    Next
    INDEX
    Explanations

    ifying words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ы
    1.89
    ์
    1.89
    сным
    1.86
    сное
    1.83
    сные
    1.82
    емо
    1.78
    oucí
    1.73
    ENTS
    1.72
    ллина
    1.72
    esy
    1.70
    POSITIVE LOGITS
    ifies
    1.75
    ifying
    1.71
    ntilde
    1.68
    ×</
    1.56
    ificación
    1.53
    ération
    1.49
    ificacion
    1.47
    ifier
    1.46
    ify
    1.44
    ified
    1.43
    Activations Density 0.702%

    No Known Activations