© 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. 150418
    Prev
    Next
    INDEX
    Explanations

    data exchange

    np_acts-logits-general · gemini-2.5-flash-lite

    necessary for legitimate

    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
    0.63
    Wherever
    0.49
     With
    0.48
    ---
    0.46
     Clear
    0.46
     the
    0.43
    With
    0.42
     another
    0.42
    0
    0.42
     Move
    0.41
    POSITIVE LOGITS
     ナイロン
    0.58
     キャップ
    0.56
     クロ
    0.55
     रच
    0.54
    デビュー
    0.54
     ちゃ
    0.52
     り
    0.51
     聞い
    0.51
     günü
    0.50
     сумка
    0.50
    Activations Density 0.000%

    No Known Activations