© 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. 63892
    Prev
    Next
    INDEX
    Explanations

    or implied

    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
    änomen
    -0.82
     oyster
    -0.75
    حيح
    -0.75
    Ingrese
    -0.75
     vicente
    -0.73
    нитель
    -0.72
    辙
    -0.72
    Hazel
    -0.71
    茴
    -0.70
    ölf
    -0.69
    POSITIVE LOGITS
     implied
    5.56
     implication
    5.34
     implications
    5.03
     implies
    4.78
     imply
    4.56
     Implications
    4.50
     implying
    4.13
     implica
    4.09
    Implications
    3.94
    imply
    3.67
    Activations Density 0.154%

    No Known Activations