© 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. 128363
    Prev
    Next
    INDEX
    Explanations

    structure with punctuation

    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
    LEY
    -0.88
    Its
    -0.88
    @_
    -0.85
    clientWidth
    -0.81
    matig
    -0.80
     of
    -0.80
     Also
    -0.79
     料金
    -0.79
     its
    -0.77
    勧め
    -0.77
    POSITIVE LOGITS
     légère
    1.01
     blancs
    0.94
     bambou
    0.94
     Singapur
    0.93
     Réseau
    0.91
     compagnon
    0.89
    Herm
    0.88
    notre
    0.88
    Hotline
    0.87
     veau
    0.87
    Activations Density 0.005%

    No Known Activations