© 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. 68712
    Prev
    Next
    INDEX
    Explanations

    phrases 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
    Ако
    -1.58
     manquer
    -1.41
    Erreur
    -1.33
     pleins
    -1.31
     étan
    -1.31
     desactivar
    -1.30
     chirurgie
    -1.30
    catori
    -1.30
     capturar
    -1.30
    镠
    -1.29
    POSITIVE LOGITS
    ha
    1.55
    la
    1.52
     as
    1.52
    !
    1.40
    ness
    1.38
    l
    1.36
     of
    1.34
    H
    1.33
    in
    1.30
     -
    1.30
    Activations Density 0.073%

    No Known Activations