© 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. 9804
    Prev
    Next
    INDEX
    Explanations

    comparison, contrast, or origin

    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
     nuestra
    0.47
     fathom
    0.46
    ங்களில்
    0.46
     aunque
    0.45
    R
    0.45
    r
    0.45
     reconsider
    0.44
     pérdida
    0.44
     doubtless
    0.44
     yerde
    0.44
    POSITIVE LOGITS
    แตก
    0.52
    龐
    0.46
    สาม
    0.45
    擠
    0.45
    ęt
    0.44
    挤
    0.43
     باغ
    0.43
    疤
    0.43
     peacock
    0.43
    圖像
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.