© 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. 25967
    Prev
    Next
    INDEX
    Explanations

    network address families

    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
     with
    -1.24
    嚙
    -1.14
     changes
    -1.14
     all
    -1.13
     evidence
    -1.11
     any
    -1.10
    haviours
    -1.09
     
    -1.07
     territ
    -1.05
     employee
    -1.04
    POSITIVE LOGITS
    Созда
    1.39
     afspraak
    1.29
    達が
    1.27
     aanbied
    1.23
    達の
    1.21
     hauptsächlich
    1.17
     resurrect
    1.17
    囔
    1.16
    好玩
    1.15
     ">=
    1.14
    Activations Density 0.005%

    No Known Activations