© 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. 26672
    Prev
    Next
    INDEX
    Explanations

    paths and file locations

    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
     gordura
    -1.40
    Özel
    -1.34
     galinha
    -1.25
     exacte
    -1.24
    groet
    -1.24
     viņ
    -1.24
    pantal
    -1.24
     braços
    -1.21
    Zeneca
    -1.20
    Neden
    -1.20
    POSITIVE LOGITS
     if
    1.70
     from
    1.13
    ","\
    1.10
     pencarian
    1.09
    breviations
    1.05
    Kenmerken
    1.02
     السياس
    1.01
     organist
    0.98
     when
    0.98
     termasuk
    0.97
    Activations Density 0.023%

    No Known Activations