© 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. 180836
    Prev
    Next
    INDEX
    Explanations

    calls to check details

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

    through online means

    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
    Fps
    0.51
    าท
    0.47
    薜
    0.42
    DummyView
    0.42
    ♤
    0.42
     изображение
    0.42
    മ്പര
    0.42
    🠀
    0.42
    BufferedWriter
    0.41
    шкина
    0.40
    POSITIVE LOGITS
     over
    0.47
     दिग्गज
    0.46
     rent
    0.46
     pemerintah
    0.46
     BJP
    0.45
     democrat
    0.45
     इनोवेशन
    0.45
     sooner
    0.45
    創新
    0.44
    verting
    0.44
    Activations Density 0.001%

    No Known Activations