© 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. 10-GEMMASCOPE-RES-131K
    7. 127821
    Prev
    Next
    INDEX
    Explanations

    description and citation

    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_10/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
     if
    -2.30
     nine
    -2.17
     while
    -2.16
     five
    -2.14
     four
    -2.05
     by
    -2.02
     seven
    -1.92
     when
    -1.91
     eight
    -1.91
     for
    -1.91
    POSITIVE LOGITS
     praticamente
    1.96
     WIL
    1.92
     extrêmement
    1.91
     continually
    1.83
    盦
    1.75
     strikingly
    1.73
     remarkably
    1.72
     Dinas
    1.72
     centaines
    1.72
     nieuwe
    1.70
    Activations Density 0.016%

    No Known Activations