© 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-262K
    7. 241421
    Prev
    Next
    INDEX
    Explanations

    tyrant

    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_262k_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
     pousse
    0.64
    odeficiency
    0.59
     Siemens
    0.59
     bateau
    0.58
     marin
    0.57
    îte
    0.57
    𝕖
    0.57
    tope
    0.55
     silic
    0.55
    쉬
    0.55
    POSITIVE LOGITS
    yr
    0.84
    yd
    0.80
     tyr
    0.78
     Tyr
    0.75
    Tyr
    0.74
    YR
    0.69
     Tyre
    0.68
    yrs
    0.66
    rys
    0.64
    τυ
    0.64
    Activations Density 0.000%

    No Known Activations