© 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. 113761
    Prev
    Next
    INDEX
    Explanations

    owner of

    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
    ."
    -2.61
    )
    -2.25
    </b>
    -2.16
     '
    -2.02
    }{
    -1.84
    }=\
    -1.77
    }$
    -1.68
    $
    -1.67
    wiada
    -1.66
    ()"
    -1.66
    POSITIVE LOGITS
     ‘‘
    2.77
    ’,
    1.94
     навіть
    1.86
     (‘
    1.85
    ’，
    1.79
    ?’
    1.74
    争议
    1.74
    虽
    1.66
    INTRODUCCIÓN
    1.65
     who
    1.64
    Activations Density 0.013%

    No Known Activations