© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45037
    Prev
    Next
    INDEX
    Explanations

    truly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0
    0.60
    re
    0.51
    1
    0.49
    ch
    0.47
    ’
    0.46
    duced
    0.46
    data
    0.45
     eng
    0.45
     rms
    0.45
    n
    0.45
    POSITIVE LOGITS
    梔
    0.48
    主義
    0.45
     acolo
    0.45
    രാഷ്ട്ര
    0.44
    ﻅ
    0.44
    ྰ
    0.44
     wiki
    0.44
    ॓
    0.42
     striving
    0.41
    eşit
    0.41
    Activations Density 0.000%

    No Known Activations