© 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. 97745
    Prev
    Next
    INDEX
    Explanations

    international business and locations

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

    demonic possession offers Gordon

    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
    kip
    0.46
    ியை
    0.45
     চাওয়া
    0.45
    qed
    0.44
     Ghosh
    0.43
    kts
    0.43
    italic
    0.42
    ]]></
    0.42
    꽉
    0.42
     στι
    0.42
    POSITIVE LOGITS
     Wikiped
    0.48
    <end_of_turn>
    0.47
     راه
    0.46
    荽
    0.46
     전문가
    0.46
     spoils
    0.46
    荅
    0.45
     EXPER
    0.44
     التط
    0.43
     እር
    0.43
    Activations Density 0.001%

    No Known Activations