© 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. 161461
    Prev
    Next
    INDEX
    Explanations

    increasing, already, penalty

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

    list items, bullet points, or direct enumeration

    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
     enjoys
    0.43
    ποτε
    0.40
     entendre
    0.40
    []
    0.39
     mitologia
    0.39
    SqlDbType
    0.39
     oversight
    0.38
     plank
    0.38
    dtd
    0.38
    shint
    0.38
    POSITIVE LOGITS
    タイム
    0.51
    ‼️
    0.51
    ティブ
    0.50
    ラス
    0.49
    ッキー
    0.48
    纓
    0.47
     कारी
    0.46
     анима
    0.46
    ꒰
    0.46
    られた
    0.45
    Activations Density 0.000%

    No Known Activations