© 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. 245879
    Prev
    Next
    INDEX
    Explanations

    southern portion

    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
    t
    0.55
    ාවිත
    0.53
    demo
    0.53
    Demo
    0.52
    dB
    0.50
    ירת
    0.49
    dokument
    0.49
    servlet
    0.49
    dok
    0.49
    wym
    0.49
    POSITIVE LOGITS
     meth
    0.42
    邊
    0.42
    hagen
    0.41
     راز
    0.40
    --;
    0.40
    とき
    0.40
     ها
    0.39
    蓬
    0.39
    ossal
    0.38
    KX
    0.38
    Activations Density 0.000%

    No Known Activations