© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 33451
    Prev
    Next
    INDEX
    Explanations

    a/in/his followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite

    complex task or request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
    а
    0.43
    aroni
    0.42
    гля
    0.41
    ation
    0.41
    avy
    0.40
     ሙሉ
    0.40
    end
    0.40
    有一个
    0.40
     ಗಮನ
    0.39
    }
    0.39
    POSITIVE LOGITS
     será
    0.50
     podrá
    0.50
     recibirá
    0.49
     phục
    0.49
     vieja
    0.49
     preparando
    0.49
     rối
    0.47
     anciennes
    0.46
     dernière
    0.46
     modernes
    0.46
    Activations Density 0.000%

    No Known Activations