© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56971
    Prev
    Next
    INDEX
    Explanations

    Go sync and group names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     шт
    -0.68
    舞蹈
    -0.66
    érité
    -0.65
     Федера
    -0.64
    Triple
    -0.62
     Pons
    -0.60
    渉
    -0.60
    bass
    -0.58
     Suns
    -0.58
    queued
    -0.58
    POSITIVE LOGITS
     group
    3.39
     groups
    3.00
    group
    2.73
     Group
    2.52
    Group
    2.48
     گروه
    2.42
     Groups
    2.42
    GROUP
    2.36
     getGroup
    2.30
     grupo
    2.28
    Activations Density 0.156%

    No Known Activations