© 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. 68179
    Prev
    Next
    INDEX
    Explanations

    code assertions and checks

    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
    hhhhh
    -0.98
    sssss
    -0.94
    ssss
    -0.89
    mmmmmm
    -0.87
    kond
    -0.85
    ««
    -0.83
    Hardness
    -0.82
    ).__
    -0.80
    holde
    -0.80
    isier
    -0.79
    POSITIVE LOGITS
     mindestens
    1.04
     it
    0.98
    これは
    0.97
    至少
    0.92
    zsef
    0.90
    intended
    0.88
     ésta
    0.88
    uvu
    0.87
    énario
    0.87
     главных
    0.87
    Activations Density 0.003%

    No Known Activations