© 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. 4972
    Prev
    Next
    INDEX
    Explanations

    among other things

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

    traffic analysis, specific data subset, high interaction

    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
    uy
    0.52
     Phang
    0.51
    l
    0.50
    i
    0.50
    il
    0.48
    o
    0.48
     Bhd
    0.48
     Seung
    0.47
    uyente
    0.47
    வியை
    0.46
    POSITIVE LOGITS
    မ္
    0.48
     imperatives
    0.45
    萫
    0.44
    鶚
    0.43
    arys
    0.43
    朹
    0.43
    ించాడు
    0.43
     aces
    0.43
     обязан
    0.42
    厷
    0.42
    Activations Density 0.000%

    No Known Activations