© 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. 129411
    Prev
    Next
    INDEX
    Explanations

    roles and domains

    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
    などを
    -1.59
     alcuni
    -1.55
     alcune
    -1.45
    サイズの
    -1.39
     vorhandenen
    -1.39
     insanely
    -1.37
     désert
    -1.35
     unmistak
    -1.35
     tendrá
    -1.34
    下意识
    -1.31
    POSITIVE LOGITS
     of
    1.85
     such
    1.84
     Before
    1.59
     However
    1.52
     Data
    1.51
     so
    1.50
     started
    1.48
     business
    1.48
     at
    1.45
     data
    1.45
    Activations Density 0.014%

    No Known Activations