© 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. 39756
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    relativeTime
    -1.21
     thọ
    -1.17
    ınıza
    -1.16
    Either
    -1.09
     portugu
    -1.09
     voegen
    -1.07
    的身
    -1.07
     jakieś
    -1.05
     לך
    -1.05
    gebob
    -1.04
    POSITIVE LOGITS
     to
    1.46
    çoit
    1.15
    g
    1.14
    E
    1.14
     as
    1.07
    <eos>
    1.07
     but
    1.02
    ± 
    1.02
     muhimu
    0.98
    n
    0.98
    Activations Density 0.031%

    No Known Activations