© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28638
    Prev
    Next
    INDEX
    Explanations

    percent values

    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
     nadar
    -1.31
     frek
    -1.27
     virke
    -1.24
    çait
    -1.22
     samti
    -1.20
    providedIn
    -1.18
     biela
    -1.18
     rød
    -1.17
     forbin
    -1.16
     editText
    -1.16
    POSITIVE LOGITS
    8
    1.24
    ac
    1.20
    ar
    1.20
    7
    1.17
    mon
    1.17
    ara
    1.17
    om
    1.15
    ga
    1.14
    al
    1.13
    va
    1.12
    Activations Density 0.007%

    No Known Activations