© 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. 196968
    Prev
    Next
    INDEX
    Explanations

    Amazon

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

    Think about

    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
     রাখেন
    0.46
     الدكتور
    0.44
     消
    0.43
     回転
    0.42
     காட்ட
    0.42
     ブラウン
    0.40
     সর্বত্র
    0.40
     പ്രതിഷേധ
    0.40
     じゃん
    0.40
     Lounge
    0.39
    POSITIVE LOGITS
    ल्ट
    0.53
    챈
    0.47
    дів
    0.47
    ao
    0.47
    ผม
    0.46
    celain
    0.45
    asts
    0.45
    licts
    0.45
    adic
    0.44
    กรรม
    0.44
    Activations Density 0.001%

    No Known Activations