© 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. 141862
    Prev
    Next
    INDEX
    Explanations

    reliefs like reinstatement

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

    AI, sensors, IDs, and strategy

    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
     cortes
    0.48
     Ravi
    0.47
    曲線
    0.45
     personnalisé
    0.45
    <unused2148>
    0.44
    aksanaan
    0.44
     courbes
    0.44
     ،
    0.43
     évol
    0.43
     قطع
    0.43
    POSITIVE LOGITS
    жа
    0.42
     Вам
    0.42
    TREE
    0.40
    we
    0.40
    सम्
    0.40
     tableaux
    0.39
    attrs
    0.39
    TEAM
    0.39
    Так
    0.38
     хотите
    0.38
    Activations Density 0.000%

    No Known Activations