© 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. 41480
    Prev
    Next
    INDEX
    Explanations

    aligned during, works with, subject to

    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
     независимо
    0.49
     Жу
    0.45
     Rama
    0.43
     lemak
    0.43
     lorsqu
    0.42
     रग
    0.42
    .}
    0.42
    ume
    0.41
    .?
    0.41
     behandling
    0.41
    POSITIVE LOGITS
    まだ
    0.51
        
    0.47
    とり
    0.45
    存在する
    0.45
    博士
    0.44
    存在的
    0.44
     עוד
    0.44
    安
    0.44
    ש
    0.42
    ちゃ
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.