© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 14882
    Prev
    Next
    INDEX
    Explanations

    references or groups

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     Settlements
    0.60
     Clos
    0.57
    accarat
    0.55
     Babylon
    0.55
     DiCaprio
    0.53
    corners
    0.52
    蠡
    0.52
     Burt
    0.52
     Buffett
    0.52
     світі
    0.52
    POSITIVE LOGITS
    耘
    0.57
     [:
    0.54
     URBAN
    0.50
     उ
    0.50
     clientes
    0.50
     rys
    0.50
     sentença
    0.49
    ướng
    0.49
     employing
    0.49
     Ü
    0.48
    Activations Density 0.000%

    No Known Activations