© 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. 22-GEMMASCOPE-RES-131K
    7. 73228
    Prev
    Next
    INDEX
    Explanations

    initials followed by punctuation

    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_22/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
     falda
    -1.67
    ólico
    -1.45
     cenu
    -1.42
    EdgeInsets
    -1.40
     hoteles
    -1.36
     novin
    -1.35
     akses
    -1.34
     ModelRenderer
    -1.34
     from
    -1.33
     áreas
    -1.33
    POSITIVE LOGITS
     například
    1.39
    ,
    1.30
     方案
    1.29
    '
    1.25
     to
    1.17
     dortmund
    1.15
     pensamentos
    1.14
     marseille
    1.08
     skrev
    1.07
     尺寸
    1.06
    Activations Density 0.001%

    No Known Activations