© 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. 141366
    Prev
    Next
    INDEX
    Explanations

    need for / ready to / proud of

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

    recursive step

    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
     metabol
    0.57
     biv
    0.48
     saraf
    0.48
     entender
    0.47
     epigen
    0.46
     come
    0.46
     zar
    0.45
     compreender
    0.45
    冑
    0.45
     metabolismo
    0.45
    POSITIVE LOGITS
    s
    0.50
    ی
    0.48
    ар
    0.48
    ים
    0.48
    念
    0.46
    هور
    0.46
    ો
    0.45
    ের
    0.45
    ષ્ટ્ર
    0.44
    Ripe
    0.43
    Activations Density 0.000%

    No Known Activations