© 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. 34-GEMMASCOPE-RES-131K
    7. 3595
    Prev
    Next
    INDEX
    Explanations

    function calls and errors

    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
    Negative Logits
    }],
    -1.29
    .")]
    -1.28
    ?',
    -1.28
    ?
    -1.20
    }]
    -1.19
    كويكب
    -1.18
     vroeger
    -1.18
     државе
    -1.17
    },{
    -1.17
    cây
    -1.14
    POSITIVE LOGITS
    :
    2.56
     -
    1.95
     has
    1.70
     –
    1.64
     got
    1.53
     gave
    1.48
     says
    1.45
     —
    1.45
     :
    1.39
     should
    1.39
    Activations Density 0.041%

    No Known Activations