© 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. 15024
    Prev
    Next
    INDEX
    Explanations

    to

    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
    っぱ
    0.64
     स्वर्ग
    0.55
    Danger
    0.54
    дко
    0.53
    Zone
    0.52
    Streak
    0.52
     devenu
    0.52
    ᵖ
    0.52
    unsafe
    0.52
     Danger
    0.51
    POSITIVE LOGITS
     fruition
    1.31
     fore
    0.98
     prominence
    0.98
    fru
    0.90
     attention
    0.89
     promin
    0.88
     terme
    0.83
     terms
    0.82
     light
    0.82
     Fru
    0.82
    Activations Density 0.040%

    No Known Activations