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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-262K
    7. 241610
    Prev
    Next
    INDEX
    Explanations

    rules or conditions

    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
     décou
    0.61
    elä
    0.60
    沔
    0.60
    schild
    0.58
    نائ
    0.58
    یکی
    0.57
     συνο
    0.57
    limiting
    0.55
     публі
    0.55
    dej
    0.55
    POSITIVE LOGITS
     establecida
    0.67
     Where
    0.67
     enforced
    0.66
     Où
    0.65
     Vom
    0.64
     実
    0.63
     budete
    0.63
     unbroken
    0.62
     rng
    0.61
     במהלך
    0.61
    Activations Density 0.001%

    No Known Activations