© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5575
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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_15_width_16k_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
    ائیں
    1.59
    каза
    1.54
    хий
    1.43
     competencias
    1.41
     predmet
    1.40
    咪
    1.38
     complémentaires
    1.38
    vaise
    1.37
     дисци
    1.36
    Platforms
    1.35
    POSITIVE LOGITS
    A
    1.88
     lage
    1.83
     anivers
    1.83
     A
    1.82
    lengths
    1.82
    ueroa
    1.81
     baud
    1.77
    weather
    1.74
    価格
    1.73
     genc
    1.73
    Activations Density 0.052%

    No Known Activations