© 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. 113557
    Prev
    Next
    INDEX
    Explanations

    gallons and their quantities

    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
     finds
    -2.66
    or
    -2.64
    rugada
    -2.23
    </b>
    -2.23
    rowable
    -2.23
    
    -2.23
     recensione
    -2.23
     leggero
    -2.16
    留意
    -2.16
     dovrebbe
    -2.14
    POSITIVE LOGITS
    <bos>
    2.95
    ↵↵
    2.50
    2
    2.16
    >//
    2.14
    l
    2.06
     signifikan
    2.02
    ⩩
    2.00
    O
    1.99
    ’.
    1.97
    C
    1.97
    Activations Density 0.003%

    No Known Activations