© 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. 193250
    Prev
    Next
    INDEX
    Explanations

    SUVs strive, success, physiology

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

    framework. Unified. Theory

    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
    omeric
    0.60
     акысыз
    0.49
    UMPS
    0.49
    arpur
    0.49
    raient
    0.48
    yCoordinate
    0.48
    vā
    0.47
    v
    0.47
    omone
    0.46
     دہشت
    0.46
    POSITIVE LOGITS
    ப்படும்
    0.47
     DOG
    0.47
     L
    0.46
    ة
    0.46
    Your
    0.46
     relation
    0.44
     William
    0.44
    الق
    0.43
    ال
    0.43
    درسة
    0.43
    Activations Density 0.000%

    No Known Activations