© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34964
    Prev
    Next
    INDEX
    Explanations

    we discuss

    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
     Институ
    -1.41
     ona
    -1.33
     mots
    -1.25
    ńska
    -1.24
     Dinas
    -1.23
     pittores
    -1.22
     situe
    -1.21
    蹀
    -1.20
     beker
    -1.19
     fokus
    -1.16
    POSITIVE LOGITS
     However
    1.71
     Since
    1.64
     Those
    1.63
     would
    1.63
     Although
    1.60
     While
    1.58
     actually
    1.52
    It
    1.45
     then
    1.45
    This
    1.44
    Activations Density 0.000%

    No Known Activations