© 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. 126355
    Prev
    Next
    INDEX
    Explanations

    Android Auto

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

    where followed by description

    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
    A
    0.50
    Management
    0.47
    (*
    0.46
    center
    0.45
     management
    0.44
     Center
    0.44
     privilegio
    0.44
    -
    0.43
    on
    0.42
    گان
    0.42
    POSITIVE LOGITS
    }}},
    0.52
     الفيزياء
    0.51
     ஸ்ப
    0.50
    迢
    0.50
    icca
    0.48
     fys
    0.48
    טר
    0.47
     বিরক্ত
    0.47
     небольшой
    0.47
     博文
    0.47
    Activations Density 0.000%

    No Known Activations