© 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. 14507
    Prev
    Next
    INDEX
    Explanations

    specific nouns and concepts

    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
     in
    -1.54
     would
    -1.45
    Also
    -1.39
     also
    -1.39
     usually
    -1.36
     of
    -1.35
     mainly
    -1.33
    also
    -1.31
     Also
    -1.27
     on
    -1.25
    POSITIVE LOGITS
     quæ
    1.23
    ἳ
    1.16
     ="";
    1.16
     bailarina
    1.13
     dokonce
    1.11
    ORDON
    1.10
     vendus
    1.09
    ⬈
    1.07
     Dinas
    1.06
    eſt
    1.05
    Activations Density 0.057%

    No Known Activations