© 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. 15331
    Prev
    Next
    INDEX
    Explanations

    technical and systems

    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
    Ａ
    0.56
    oxone
    0.55
     adolescente
    0.54
    chae
    0.52
     Cane
    0.52
    rick
    0.51
    個
    0.51
    薯
    0.51
    ﾘ
    0.50
     مار
    0.50
    POSITIVE LOGITS
     cowboys
    0.59
     complainants
    0.57
     stuffing
    0.54
     Accord
    0.54
     wrangler
    0.54
    毙
    0.54
    ᆢ
    0.54
     sial
    0.53
     dwellers
    0.53
     stuff
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.