© 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. 72668
    Prev
    Next
    INDEX
    Explanations

    names followed by actions

    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
     from
    -1.74
     their
    -1.58
     gezwungen
    -1.33
     which
    -1.29
    During
    -1.27
    )}
    -1.27
    Even
    -1.23
     насеља
    -1.20
    All
    -1.19
     During
    -1.19
    POSITIVE LOGITS
     was
    1.87
     didn
    1.73
    が
    1.65
     wasn
    1.61
     couldn
    1.39
    については
    1.39
     evidentemente
    1.39
     entrando
    1.34
     praticamente
    1.31
     ของ
    1.27
    Activations Density 0.025%

    No Known Activations