© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68401
    Prev
    Next
    INDEX
    Explanations

    Asai

    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
     '>=
    -2.66
    琤
    -2.63
     ""
    -2.56
    廔
    -2.56
    聍
    -2.52
     }),
    -2.48
    ם
    -2.47
    []
    -2.47
    沄
    -2.47
    颙
    -2.45
    POSITIVE LOGITS
    }
    3.55
    -
    3.52
     
    3.52
    --
    3.09
    y
    2.86
    看上去
    2.75
    )
    2.66
    jenige
    2.64
    it
    2.61
     spearheaded
    2.53
    Activations Density 0.019%

    No Known Activations