© 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. 132307
    Prev
    Next
    INDEX
    Explanations

    appear across | price tag | measures and

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

    common names, titles, objects

    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
    дового
    0.45
    항공
    0.44
    PLE
    0.44
    ITZ
    0.44
    オ
    0.43
    GMT
    0.43
    デート
    0.42
     airways
    0.42
    DS
    0.42
    VENUE
    0.42
    POSITIVE LOGITS
    ourcen
    0.47
    rai
    0.46
     л
    0.45
     μορ
    0.44
     eingel
    0.44
     propias
    0.43
    ứ
    0.43
    tbLabel
    0.43
     ausdr
    0.43
     formes
    0.42
    Activations Density 0.002%

    No Known Activations