© 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. 33305
    Prev
    Next
    INDEX
    Explanations

    struct definitions

    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
     first
    -1.35
     to
    -1.18
     entire
    -1.05
     various
    -1.02
     many
    -1.02
     rest
    -1.01
     underlying
    -1.00
     أعلام
    -1.00
     some
    -0.99
     algunos
    -0.96
    POSITIVE LOGITS
     febr
    1.13
    ACHUSETTS
    1.05
     efficace
    1.02
     فإن
    0.98
     вре
    0.96
     behöver
    0.93
     produkter
    0.93
     vanille
    0.93
    0.92
     thuis
    0.92
    Activations Density 0.021%

    No Known Activations