© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200184
    Prev
    Next
    INDEX
    Explanations

    package files needed

    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
    Negative Logits
    ،
    0.47
     methodology
    0.42
     newsletters
    0.41
     چیر
    0.40
    ，
    0.40
     Tash
    0.38
    䉽
    0.38
    敉
    0.38
    $,
    0.37
     authors
    0.37
    POSITIVE LOGITS
    F
    0.48
    Relax
    0.47
    Anime
    0.46
    ပြီး
    0.45
    Travel
    0.44
    FAKE
    0.43
    Paint
    0.42
    P
    0.42
    でお
    0.42
     exigences
    0.42
    Activations Density 0.008%

    No Known Activations