© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70808
    Prev
    Next
    INDEX
    Explanations

    Professor titles and awards

    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
     severa
    -1.16
     PHOSPH
    -1.14
    concep
    -1.08
     FERT
    -1.07
    imee
    -1.07
    despite
    -1.06
    ergies
    -1.04
     STRATEGY
    -1.04
     WEDDING
    -1.04
     direc
    -1.02
    POSITIVE LOGITS
     for
    1.40
     durch
    1.24
     so
    1.21
    +}\
    1.16
     voor
    1.12
     bagi
    1.12
    .*")]
    1.09
     by
    1.08
     questo
    1.08
     their
    1.07
    Activations Density 0.026%

    No Known Activations