© 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. 47168
    Prev
    Next
    INDEX
    Explanations

    highest quality resources

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

    asking for clarification

    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
     當
    0.58
     ওয়ে
    0.52
     由于
    0.52
     h
    0.47
     कृ
    0.46
     နဲ့
    0.46
     وين
    0.46
     Combien
    0.46
     BLE
    0.45
     Schm
    0.45
    POSITIVE LOGITS
    Ди
    0.49
    镐
    0.43
    enswert
    0.43
    군의
    0.43
    野
    0.42
    岐阜
    0.42
    ographystyle
    0.41
    FM
    0.41
    小数
    0.41
    őd
    0.41
    Activations Density 0.001%

    No Known Activations