© 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. 180266
    Prev
    Next
    INDEX
    Explanations

    fine enough

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

    focus on specific actions

    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
    Negative Logits
     budu
    0.57
     kampany
    0.50
     previews
    0.49
     menampilkan
    0.48
     preview
    0.47
     nickname
    0.46
     queremos
    0.45
     phir
    0.45
     wrinkle
    0.45
    ת
    0.45
    POSITIVE LOGITS
    js
    0.53
    _=
    0.50
    hydro
    0.47
    startDate
    0.47
    prison
    0.47
    ᕋ
    0.47
    scient
    0.47
    indx
    0.46
     Компания
    0.46
    我
    0.46
    Activations Density 0.001%

    No Known Activations