© 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. 10-GEMMASCOPE-RES-131K
    7. 72042
    Prev
    Next
    INDEX
    Explanations

    css property separators

    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_10/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
     it
    -1.65
     such
    -1.59
    providedIn
    -1.58
     be
    -1.49
    -1.49
    xvii
    -1.48
    Он
    -1.43
    ৳
    -1.41
     so
    -1.41
     USSR
    -1.38
    POSITIVE LOGITS
     colorear
    1.45
    Misión
    1.27
    OfThe
    1.25
    ised
    1.25
    setzen
    1.22
    其余
    1.21
    ↵↵
    1.20
     of
    1.19
     ricerca
    1.18
     vox
    1.18
    Activations Density 0.018%

    No Known Activations