© 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. 106959
    Prev
    Next
    INDEX
    Explanations

    crochet hook, universal calling

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

    beat drops

    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
     or
    0.52
    停止
    0.49
    ionalmente
    0.42
    lež
    0.40
     Pearson
    0.40
     demikian
    0.40
     Shots
    0.39
    h
    0.39
    レーション
    0.39
     Tumblr
    0.39
    POSITIVE LOGITS
    ਹਿ
    0.52
     대체
    0.52
    𝘦
    0.50
     değeri
    0.50
    ೫
    0.49
    가가
    0.49
     เวอร์
    0.47
    OTH
    0.46
    𝘖
    0.46
     stepfather
    0.45
    Activations Density 0.000%

    No Known Activations