© 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. 143069
    Prev
    Next
    INDEX
    Explanations

    entrepreneurs, moves, all

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

    arranging options and explanations

    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
    >©
    0.49
     awarded
    0.46
     attachments
    0.43
    ристо
    0.42
     exempt
    0.42
     amounts
    0.42
     固定
    0.42
    免
    0.41
     proceeds
    0.41
     tetrahydro
    0.40
    POSITIVE LOGITS
     Scheduler
    0.52
    tes
    0.47
     Necklace
    0.47
    ların
    0.47
     Graph
    0.47
     அல்லது
    0.46
    战争
    0.46
     ক্ষুধা
    0.46
    蓆
    0.45
     Rejected
    0.45
    Activations Density 0.000%

    No Known Activations