© 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. 122678
    Prev
    Next
    INDEX
    Explanations

    branding and permissions

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

    optimization levels or warnings

    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
     యూని
    0.54
    纰
    0.51
     तकनीकी
    0.50
     lưng
    0.49
     폭
    0.49
     đỡ
    0.48
     добро
    0.48
     পানির
    0.48
    号码
    0.47
     הפר
    0.47
    POSITIVE LOGITS
    IV
    0.53
     provides
    0.52
    Т
    0.50
    IOT
    0.49
    Detailed
    0.49
     recounted
    0.47
    ES
    0.46
    SER
    0.46
    Based
    0.46
    (?:
    0.46
    Activations Density 0.001%

    No Known Activations