© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63629
    Prev
    Next
    INDEX
    Explanations

    version control tags and file delimiters

    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_34/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
    샐
    -0.89
    豸
    -0.82
     your
    -0.81
    TokenNameLPAREN
    -0.80
     kilom
    -0.79
     kompon
    -0.77
     puzzle
    -0.76
    ující
    -0.76
    ullo
    -0.76
    erequisites
    -0.76
    POSITIVE LOGITS
     end
    1.77
     EOF
    1.70
    EOF
    1.59
     vim
    1.59
     END
    1.57
    END
    1.41
    eof
    1.41
     eof
    1.38
    end
    1.33
     End
    1.30
    Activations Density 0.031%

    No Known Activations