© 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. 36291
    Prev
    Next
    INDEX
    Explanations

    constructor arguments or return types

    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
    ≔
    -1.16
    šč
    -1.13
     herbes
    -1.08
    -1.08
     après
    -1.07
     Barça
    -1.06
    由于
    -1.05
     nobili
    -1.05
     massiv
    -1.05
     tiden
    -1.05
    POSITIVE LOGITS
     or
    1.40
     out
    1.30
     in
    1.26
     was
    1.22
     vermutlich
    1.16
     we
    1.13
     from
    1.12
     should
    1.11
     on
    1.08
     I
    1.06
    Activations Density 0.001%

    No Known Activations