© 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-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1229
    Prev
    Next
    INDEX
    Explanations

    from + start/time indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ery
    1.77
    d
    1.73
    è
    1.67
    ig
    1.63
    do
    1.62
    ical
    1.61
    ick
    1.60
    ated
    1.60
    ine
    1.59
     with
    1.57
    POSITIVE LOGITS
     afar
    2.92
    luoro
    2.44
     whence
    2.43
    ղ
    2.36
    นั้น
    2.34
     segi
    2.31
     stdin
    2.30
    çoivent
    2.30
     fingert
    2.27
    ccak
    2.26
    Activations Density 0.158%

    No Known Activations