© 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. 185881
    Prev
    Next
    INDEX
    Explanations

    sample profile, additional information

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

    driving with a

    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
    ва
    0.54
    ан
    0.54
     중심
    0.53
    ார்கள்
    0.52
    нак
    0.52
    види
    0.51
    බ
    0.51
     типи
    0.50
    ceptors
    0.50
    блю
    0.49
    POSITIVE LOGITS
     Best
    0.54
     Legislative
    0.52
     nr
    0.50
     na
    0.49
     j
    0.47
     Legislature
    0.47
     Pharmacy
    0.47
    న్య
    0.47
     nth
    0.46
     Bus
    0.46
    Activations Density 0.002%

    No Known Activations