© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127421
    Prev
    Next
    INDEX
    Explanations

    height, support, import, products, shared

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

    case Assessment Features

    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
    oe
    0.48
    octrl
    0.45
    abases
    0.44
    वेलकम
    0.44
    ChatGPT
    0.44
    ၾ
    0.44
    init
    0.44
    controllers
    0.44
    covid
    0.43
    okan
    0.43
    POSITIVE LOGITS
     siquiera
    0.49
     chub
    0.46
    늄
    0.44
     Glu
    0.42
     Natl
    0.42
     sli
    0.42
     gamanam
    0.41
    酯
    0.41
    化物
    0.41
    ,/
    0.40
    Activations Density 0.001%

    No Known Activations