© 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. 127799
    Prev
    Next
    INDEX
    Explanations

    please and requests

    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
    
    -1.88
    耄
    -1.80
    ፨
    -1.70
    賡
    -1.62
    sivamente
    -1.59
    PEZ
    -1.59
    鮟
    -1.58
    lossing
    -1.58
    Jeudi
    -1.57
    sibilità
    -1.56
    POSITIVE LOGITS
    or
    2.39
    a
    2.38
    3
    2.23
    }
    2.08
    2
    2.02
    as
    1.98
    l
    1.91
     или
    1.84
     /
    1.82
    are
    1.80
    Activations Density 0.006%

    No Known Activations