© 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. 26786
    Prev
    Next
    INDEX
    Explanations

    editor in chief is

    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
     then
    -1.57
     napisał
    -1.45
    :'',
    -1.44
    :"",
    -1.43
     our
    -1.40
     szczeg
    -1.35
     any
    -1.23
    )();
    -1.23
     \%$,
    -1.22
    errno
    -1.21
    POSITIVE LOGITS
     currently
    1.73
    currently
    1.60
    Currently
    1.45
     pompe
    1.39
     funcionários
    1.38
    前は
    1.38
    ществует
    1.36
    recently
    1.34
    woordig
    1.34
    Its
    1.33
    Activations Density 0.307%

    No Known Activations