© 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. 48285
    Prev
    Next
    INDEX
    Explanations

    years, bottle, bombs, Mediterranean

    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
     Comprehensive
    0.42
    /
    0.40
    েল
    0.38
     Dioc
    0.38
    )
    0.37
    ential
    0.37
     Pregnancy
    0.37
     Hepatitis
    0.37
     intensive
    0.37
     refrigeration
    0.36
    POSITIVE LOGITS
     otak
    0.49
     معايا
    0.47
    guys
    0.47
    طيكم
    0.46
    媤
    0.46
     kane
    0.46
    BLACKLIST
    0.46
    ק
    0.45
     ước
    0.45
     पेज
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.