© 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. 14935
    Prev
    Next
    INDEX
    Explanations

    abstract concepts

    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
    ニン
    0.63
     Cil
    0.62
    Chill
    0.61
    Thai
    0.59
     Góc
    0.59
    Css
    0.58
    ᑕ
    0.58
    Gui
    0.58
    conten
    0.57
    Ջ
    0.57
    POSITIVE LOGITS
    istico
    0.58
     signal
    0.57
     inventor
    0.55
     invention
    0.54
     shutters
    0.54
     signaling
    0.53
     time
    0.52
     archery
    0.52
     архі
    0.51
     programming
    0.51
    Activations Density 0.000%

    No Known Activations