© 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. 26830
    Prev
    Next
    INDEX
    Explanations

    impulse, 彼が, term, norms, script, merged, Use, received

    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
    Technische
    0.49
    вари
    0.48
    ガス
    0.48
    艐
    0.47
    廃棄
    0.46
    グ
    0.46
    ㎎
    0.45
    туре
    0.44
     Pfeiffer
    0.44
    Measurement
    0.44
    POSITIVE LOGITS
     এদের
    0.54
     midweek
    0.50
    );
    0.49
     Normally
    0.49
     idiots
    0.48
     hoodies
    0.48
      
    0.47
     amongst
    0.47
    dogs
    0.47
     outsiders
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.