© 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. 15593
    Prev
    Next
    INDEX
    Explanations

    interpreter code evaluation

    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
    adhyay
    -1.38
    arbeitung
    -1.12
     avea
    -1.06
     şir
    -1.06
     '+':
    -1.05
    masing
    -1.02
    romolecules
    -1.01
     manicura
    -1.01
     LEAVE
    -1.00
    این
    -1.00
    POSITIVE LOGITS
     so
    1.35
     would
    1.17
     to
    1.14
     like
    1.13
     menciona
    1.09
    ’
    1.05
     doesn
    1.04
     gefangen
    0.96
     One
    0.96
     there
    0.95
    Activations Density 0.001%

    No Known Activations