© 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. 22247
    Prev
    Next
    INDEX
    Explanations

    writing content

    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
    ’
    -2.19
    dzić
    -1.84
    oração
    -1.83
    }
    -1.67
     durch
    -1.66
    ícias
    -1.64
    ;
    -1.63
    了一下
    -1.60
     chico
    -1.59
    istán
    -1.57
    POSITIVE LOGITS
    鏐
    2.13
    鉭
    2.06
     решила
    2.05
    썽
    1.92
    section
    1.90
    佮
    1.88
    èdent
    1.86
    たまたま
    1.84
     Behaup
    1.77
     toallas
    1.77
    Activations Density 0.012%

    No Known Activations