© 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. 14870
    Prev
    Next
    INDEX
    Explanations

    returns data

    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
    their
    0.71
    strlen
    0.70
    ":(
    0.69
    (*(
    0.68
    Integer
    0.68
    ))}
    0.68
    parseInt
    0.67
     their
    0.66
    strcmp
    0.65
    *((*
    0.64
    POSITIVE LOGITS
     Cloning
    0.73
     очи
    0.72
     rejuvenated
    0.71
     Clone
    0.71
     Stabil
    0.70
     embellished
    0.67
     rejuvenating
    0.67
     Copy
    0.66
     embell
    0.66
     copiar
    0.66
    Activations Density 0.002%

    No Known Activations