© 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. 80796
    Prev
    Next
    INDEX
    Explanations

    academic and software development

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

    development environments and platforms

    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
    6
    1.10
    7
    1.00
    .
    0.97
    8
    0.95
    4
    0.94
    1
    0.93
    5
    0.86
    3
    0.82
    은
    0.77
    </strong>
    0.75
    POSITIVE LOGITS
    galkan
    0.71
    ({\
    0.70
    is
    0.67
    曛
    0.67
    '')
    0.67
    л
    0.67
     and
    0.64
    ق
    0.64
    trashItem
    0.63
    ل
    0.63
    Activations Density 0.045%

    No Known Activations