© 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. 22-GEMMASCOPE-RES-131K
    7. 128844
    Prev
    Next
    INDEX
    Explanations

    talks and presentations

    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_22/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
     only
    -1.44
     or
    -1.32
    рачи
    -1.04
     just
    -1.04
    ׇ
    -1.02
     this
    -1.02
     hukuman
    -1.00
     penghar
    -0.99
    나는
    -0.98
     because
    -0.98
    POSITIVE LOGITS
     was
    1.87
     how
    1.41
     current
    1.18
     souver
    1.16
     وكانت
    1.14
    AfterViewInit
    1.11
     rapidement
    1.11
     overview
    1.10
     ſeveral
    1.10
     recent
    1.09
    Activations Density 0.015%

    No Known Activations