© 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. 129371
    Prev
    Next
    INDEX
    Explanations

    slice and sliced food and data

    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
    诂
    -2.42
     Actually
    -2.39
     Originally
    -2.38
     Certainly
    -2.34
    毟
    -2.27
     Currently
    -2.25
     Around
    -2.20
     Almost
    -2.20
     While
    -2.20
    </strong>
    -2.20
    POSITIVE LOGITS
    茕
    2.61
    桄
    2.36
    ），
    2.31
    ⟐
    2.17
     عندما
    2.17
     enorme
    2.16
    がいい
    2.16
    驺
    2.14
    
    2.14
     hermé
    2.14
    Activations Density 0.006%

    No Known Activations