© 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
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15347
    Prev
    Next
    INDEX
    Explanations

    identity and recovery

    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
     proinflammatory
    0.61
    constraintlayout
    0.57
    익
    0.54
    attiv
    0.54
     intermolecular
    0.53
    Molecular
    0.52
     antioxidant
    0.52
    Lem
    0.52
     confeder
    0.51
    Tek
    0.51
    POSITIVE LOGITS
     Neces
    0.59
     decreed
    0.54
     Assume
    0.54
    _{*}\
    0.54
     mát
    0.54
     sente
    0.53
     firmy
    0.53
     令
    0.53
     fera
    0.52
     hoeveel
    0.52
    Activations Density 0.000%

    No Known Activations