© 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. 3226
    Prev
    Next
    INDEX
    Explanations

    encyclopedia handbook chapter references

    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
     paper
    -0.96
    yx
    -0.85
     thấp
    -0.82
     could
    -0.81
     students
    -0.81
     almost
    -0.80
     especially
    -0.78
     used
    -0.78
     those
    -0.77
     representatives
    -0.77
    POSITIVE LOGITS
     Encyclopedia
    1.27
     Handbook
    1.15
    Encyclopedia
    1.11
    chapter
    1.11
     Springer
    1.11
     chapitre
    1.09
    Springer
    1.09
     encyclopedia
    1.07
    Handbook
    1.04
     chapters
    1.02
    Activations Density 0.032%

    No Known Activations