© 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-262K
    7. 241554
    Prev
    Next
    INDEX
    Explanations

    items and products

    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_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
     ('
    0.65
     ['
    0.59
     (?
    0.52
     ($
    0.52
    afi
    0.52
    σίας
    0.51
    hipi
    0.50
    itelja
    0.50
    toolbar
    0.50
    ×</
    0.50
    POSITIVE LOGITS
     inductance
    0.63
     бонусы
    0.63
     delusions
    0.63
    ">—
    0.63
     smach
    0.61
     basın
    0.61
    ")[
    0.60
    LookAnd
    0.60
     mith
    0.60
    धन
    0.59
    Activations Density 0.000%

    No Known Activations