© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 218731
    Prev
    Next
    INDEX
    Explanations

    comes calling

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

    understanding elements

    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
     ម
    0.71
     Considerando
    0.55
     モン
    0.54
     Auswirkungen
    0.54
     Sobre
    0.53
     Наи
    0.52
     だ
    0.50
     Пре
    0.50
     Миха
    0.50
     изображение
    0.50
    POSITIVE LOGITS
     Philly
    0.43
    你自己
    0.43
    áter
    0.42
    围绕
    0.41
     innych
    0.40
    ici
    0.40
    其他
    0.40
    ués
    0.40
    有趣的
    0.40
    (
    0.39
    Activations Density 0.000%

    No Known Activations