© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82378
    Prev
    Next
    INDEX
    Explanations

    see how it unfolds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     magnified
    0.48
    َص
    0.48
     abducted
    0.47
    是可以
    0.47
    ObjectIndex
    0.46
     eclipsed
    0.46
     attiv
    0.46
    ರುತ್ತದೆ
    0.45
     predominate
    0.44
    ній
    0.44
    POSITIVE LOGITS
    Cd
    0.48
    ̧
    0.45
    ik
    0.44
    лимпий
    0.42
    im
    0.42
    academia
    0.41
     gere
    0.40
     $_{
    0.40
     разли
    0.40
    ledes
    0.39
    Activations Density 0.002%

    No Known Activations