© 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. 58287
    Prev
    Next
    INDEX
    Explanations

    ability to generate or explain

    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
     vanguard
    0.40
     çarp
    0.39
    П
    0.39
     L
    0.38
     mayhem
    0.38
     violently
    0.38
     Liebig
    0.38
     impetus
    0.38
     OnTrigger
    0.38
     Violence
    0.37
    POSITIVE LOGITS
     پوست
    0.44
    łon
    0.43
    豢
    0.42
     цере
    0.42
    getConfiguration
    0.41
     ১
    0.41
     त्व
    0.41
    ત્વ
    0.41
     डाइट
    0.41
    রাষ্ট্রে
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.