© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98258
    Prev
    Next
    INDEX
    Explanations

    file path 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_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
    <bos>
    -1.37
    かで
    -1.10
     to
    -1.09
     jeszcze
    -1.03
    žnost
    -1.02
    で
    -1.00
     in
    -0.99
    を
    -0.98
    vereign
    -0.98
     they
    -0.98
    POSITIVE LOGITS
    の時に
    1.24
     hombros
    1.20
     empê
    1.20
    ⵌ
    1.20
     sudad
    1.20
    もうすぐ
    1.19
    えっ
    1.16
    なんですね
    1.16
     Transfermarkt
    1.15
    Ϋ
    1.15
    Activations Density 0.018%

    No Known Activations