© 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. 72351
    Prev
    Next
    INDEX
    Explanations

    multi-lingual, diverse topics

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

    strength, cause, here, blackjack

    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
    总结
    0.47
    ％
    0.46
    一
    0.46
    信
    0.45
    帆
    0.44
    华为
    0.44
     Logs
    0.44
    用
    0.44
    央
    0.44
    ാന
    0.44
    POSITIVE LOGITS
     γνωσ
    0.52
     अभिन्न
    0.49
     щодо
    0.48
     কাশি
    0.46
    amiento
    0.46
     restitution
    0.45
     sejumlah
    0.45
     बाय
    0.45
    ammad
    0.45
    adeso
    0.45
    Activations Density 0.000%

    No Known Activations