© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13031
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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
     babys
    0.58
     childcare
    0.51
    大使
    0.50
    ϫ
    0.50
     жела
    0.50
    ∝
    0.50
     гг
    0.49
     počet
    0.49
     গুলির
    0.49
     cavern
    0.48
    POSITIVE LOGITS
     अभिन्न
    0.55
    '=>'','
    0.53
    plements
    0.52
     बजकर
    0.51
    แรม
    0.51
    yfikacji
    0.51
    ahr
    0.50
    furan
    0.50
    ާ
    0.50
     соль
    0.49
    Activations Density 0.037%

    No Known Activations