© 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. 132043
    Prev
    Next
    INDEX
    Explanations

    in flashlight

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

    lists of components and their function

    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
    视为
    0.46
     τρόπο
    0.43
    рав
    0.43
     поня
    0.43
    앱
    0.43
    ╋
    0.43
    㗽
    0.42
     மேற்பட்ட
    0.42
    తులను
    0.42
    构
    0.42
    POSITIVE LOGITS
    previous
    0.51
     ilm
    0.48
     vorige
    0.45
     (\%)
    0.44
     stoked
    0.44
    esthesia
    0.44
    waukee
    0.43
    Charges
    0.43
    </th>
    0.43
    kach
    0.43
    Activations Density 0.000%

    No Known Activations