© 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. 20879
    Prev
    Next
    INDEX
    Explanations

    years and numbers

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

    historical events and politics

    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
     semigroup
    0.40
     pendientes
    0.40
     marginRight
    0.40
     मिले
    0.39
     marginLeft
    0.39
     مس
    0.38
     Quaternion
    0.38
     ല
    0.38
    স্পতি
    0.38
     थिएटर
    0.38
    POSITIVE LOGITS
    왔
    0.43
    кратно
    0.43
    ă
    0.43
     вами
    0.41
    The
    0.40
    ‚¬
    0.39
    Você
    0.38
    ə
    0.38
    D
    0.38
    Sh
    0.38
    Activations Density 0.067%

    No Known Activations