© 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. 63997
    Prev
    Next
    INDEX
    Explanations

    us a

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

    lists items and descriptions

    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
    но
    0.46
    Kiev
    0.44
    на
    0.44
    aina
    0.43
    hemm
    0.43
    実績
    0.42
    efeated
    0.42
    桻
    0.42
    喏
    0.42
     valmist
    0.41
    POSITIVE LOGITS
    ιβ
    0.44
     ({
    0.43
     ('
    0.43
     Physica
    0.41
    nib
    0.41
     "(
    0.41
     theyre
    0.41
    फिज
    0.41
     wines
    0.40
     barter
    0.40
    Activations Density 0.000%

    No Known Activations