© 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. 202076
    Prev
    Next
    INDEX
    Explanations

    states, roles, and scale

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

    bulls and red myths

    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
     ܡ
    0.52
     basados
    0.51
     சீன
    0.50
    žka
    0.48
     사용하는
    0.48
     conectado
    0.47
    사용
    0.47
     συνεχ
    0.46
     ކުރ
    0.46
    忤
    0.45
    POSITIVE LOGITS
    lie
    0.42
     a
    0.42
     Absence
    0.38
     postponement
    0.38
     MIME
    0.38
     an
    0.38
     stomachs
    0.38
     acres
    0.38
     lễ
    0.38
     innermost
    0.38
    Activations Density 0.000%

    No Known Activations