© 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. 26271
    Prev
    Next
    INDEX
    Explanations

    ClientID, Path, id, name

    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
     Also
    -0.96
     ovviamente
    -0.93
    They
    -0.88
     are
    -0.87
     Gå
    -0.86
     wrappers
    -0.85
     tentu
    -0.83
    will
    -0.83
     luoghi
    -0.83
     The
    -0.82
    POSITIVE LOGITS
     названием
    1.14
    鳖
    1.05
    zepine
    1.03
     templo
    0.96
    wości
    0.96
    Scorpio
    0.95
    それは
    0.93
    ₸
    0.93
     mijn
    0.93
    骤
    0.93
    Activations Density 0.007%

    No Known Activations