© 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. 243694
    Prev
    Next
    INDEX
    Explanations

    specific noun phrases

    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
    劍
    0.48
    Á
    0.46
     अफगानिस्तान
    0.45
     desmont
    0.45
    ير
    0.44
    ą
    0.44
    종
    0.44
    運動
    0.44
    法の
    0.44
    ARK
    0.43
    POSITIVE LOGITS
    equiv
    0.49
    dominant
    0.45
    全市
    0.45
    selective
    0.44
    recursive
    0.43
    тельностью
    0.43
    exclusive
    0.43
     Tues
    0.43
    ллина
    0.42
     لئے
    0.42
    Activations Density 0.000%

    No Known Activations