© 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. 34-GEMMASCOPE-RES-131K
    7. 62877
    Prev
    Next
    INDEX
    Explanations

    code delimiters or structure

    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
    eroen
    -0.82
     atk
    -0.78
    klub
    -0.76
    ecutable
    -0.75
    documentation
    -0.74
     might
    -0.73
     justement
    -0.73
    COURS
    -0.72
     carbone
    -0.72
     sada
    -0.71
    POSITIVE LOGITS
    modities
    0.80
    分けて
    0.75
    istocene
    0.75
    }^{*}$
    0.74
    Ezek
    0.74
    IAS
    0.73
     함
    0.73
    小结
    0.73
     picks
    0.72
     UTF
    0.71
    Activations Density 0.002%

    No Known Activations