© 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. 129067
    Prev
    Next
    INDEX
    Explanations

    control flow and return statements

    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
     from
    -1.38
    Trichloroethane
    -1.34
    ụn
    -1.25
     máte
    -1.24
    𓄹
    -1.23
     Gemeinsame
    -1.22
    тифика
    -1.21
    tyimages
    -1.21
     nová
    -1.19
    陝
    -1.18
    POSITIVE LOGITS
    es
    1.65
    ir
    1.61
    u
    1.55
    is
    1.52
    i
    1.41
    ur
    1.41
    are
    1.38
    <bos>
    1.38
    om
    1.32
     häufiger
    1.31
    Activations Density 0.008%

    No Known Activations