© 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. 31438
    Prev
    Next
    INDEX
    Explanations

    Station, Department, Skyline

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

    not anymore

    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
    et
    0.46
     Бог
    0.45
    やった
    0.44
    錯
    0.44
     marsh
    0.41
    busy
    0.41
    jos
    0.41
    marshalling
    0.41
     holly
    0.40
    util
    0.39
    POSITIVE LOGITS
    吒
    0.49
    هي
    0.47
    னின்
    0.45
    ресень
    0.44
    ременно
    0.44
    หลด
    0.44
    ANDS
    0.43
    IMATE
    0.43
     narrowband
    0.43
     कैंड
    0.43
    Activations Density 0.000%

    No Known Activations