© 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. 125997
    Prev
    Next
    INDEX
    Explanations

    professional context

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

    examples with "how to"

    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
    આ
    0.54
    له
    0.50
    romet
    0.49
    ὅ
    0.49
    ❶
    0.48
    oulos
    0.48
    𝒓
    0.48
    airs
    0.47
    actifs
    0.46
    วันที่
    0.46
    POSITIVE LOGITS
     an
    0.52
    p
    0.47
     impeachment
    0.46
     ancillary
    0.45
     adverb
    0.45
     señ
    0.44
     gemacht
    0.44
    g
    0.44
     itinerant
    0.44
     adjunct
    0.43
    Activations Density 0.000%

    No Known Activations