© 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. 129963
    Prev
    Next
    INDEX
    Explanations

    min, max, boundaries, days

    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
     även
    -0.97
     takto
    -0.96
     mêmes
    -0.92
     myös
    -0.91
     også
    -0.90
     auch
    -0.88
    fangen
    -0.87
     progrès
    -0.85
    hidup
    -0.85
    lysses
    -0.85
    POSITIVE LOGITS
     already
    1.02
     some
    0.95
     as
    0.95
     instantly
    0.92
     constituents
    0.90
     suplementos
    0.89
    parametrize
    0.87
     other
    0.85
     examples
    0.85
     slightly
    0.85
    Activations Density 0.002%

    No Known Activations