© 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. 24693
    Prev
    Next
    INDEX
    Explanations

    locations and foreign names

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

    forms part of, what it is

    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
    .
    0.19
    -
    0.19
     mathvariant
    0.17
     N
    0.17
    (
    0.17
    ,
    0.16
     rRNA
    0.16
     the
    0.16
     M
    0.15
     U
    0.15
    POSITIVE LOGITS
     उक्त
    0.18
     மேலே
    0.18
    ோவின்
    0.18
     momentous
    0.17
     повин
    0.17
     murderous
    0.17
     distraught
    0.17
    КА
    0.17
     ስለዚህ
    0.16
     wretched
    0.16
    Activations Density 0.301%

    No Known Activations