© 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. 138295
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and values

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

    type="

    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
    usus
    0.44
    ulg
    0.43
    tek
    0.41
     が
    0.40
    igur
    0.40
    ILA
    0.40
    iglio
    0.40
    VAL
    0.39
     ۶
    0.39
    ethylene
    0.39
    POSITIVE LOGITS
     banished
    0.48
    .],
    0.47
     Antoine
    0.47
     đoàn
    0.44
     Rentals
    0.43
     Tennis
    0.43
    *;
    0.42
    .'),
    0.41
    _',
    0.41
    ;*/
    0.41
    Activations Density 0.000%

    No Known Activations