© 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. 15087
    Prev
    Next
    INDEX
    Explanations

    software tasks

    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
    Merhaba
    0.55
    هرة
    0.55
     ہاں
    0.54
    Hepinize
    0.54
    ToBase
    0.53
    romo
    0.52
     بسم
    0.51
    📰
    0.51
     ગયો
    0.50
    ₹
    0.50
    POSITIVE LOGITS
     dá
    0.70
     SEQU
    0.66
     perceptible
    0.65
     Extreme
    0.65
     answer
    0.64
     Answer
    0.60
     immuno
    0.59
    极端
    0.59
     POT
    0.58
     ECG
    0.58
    Activations Density 0.000%

    No Known Activations