© 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. 47775
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
     noticias
    -1.00
    gridx
    -0.81
    槻
    -0.78
     SMG
    -0.77
    ٗ
    -0.73
     Bc
    -0.72
    romycin
    -0.72
    gues
    -0.72
    톱
    -0.70
    chitis
    -0.69
    POSITIVE LOGITS
     Rest
    1.44
    Rest
    1.30
     Annotation
    1.20
     REST
    1.13
     rested
    1.11
     annotation
    1.09
    REST
    1.08
     rest
    1.05
     Wig
    1.03
    Annotation
    1.01
    Activations Density 0.028%

    No Known Activations