© 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. 60247
    Prev
    Next
    INDEX
    Explanations

    foreign words and texts

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

    different questions, hiring people, structuring, yielding

    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
     BOAT
    0.45
     hapl
    0.44
    emph
    0.44
    घ
    0.44
    ﻘ
    0.43
     Aviv
    0.42
     declines
    0.42
    ब
    0.42
    批发
    0.42
    𒅗
    0.42
    POSITIVE LOGITS
     інші
    0.52
    inį
    0.48
     машиналарын
    0.46
     иных
    0.46
     ሌሎች
    0.45
    acky
    0.45
     інших
    0.45
    blers
    0.44
     других
    0.44
     مزید
    0.43
    Activations Density 0.000%

    No Known Activations