© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8565
    Prev
    Next
    INDEX
    Explanations

    code snippets, markdown, URLs

    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
     is
    -1.74
     and
    -1.66
     the
    -1.66
    -
    -1.59
     lecteurs
    -1.31
    所说的
    -1.30
     acogedor
    -1.25
     voisins
    -1.23
     its
    -1.21
    颱
    -1.20
    POSITIVE LOGITS
     to
    1.68
    medriver
    1.61
     memutus
    1.59
     большого
    1.59
    vantaged
    1.56
     consectetur
    1.55
     melewati
    1.52
     способов
    1.50
     Especific
    1.50
     jenen
    1.47
    Activations Density 0.025%

    No Known Activations