© 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. 25901
    Prev
    Next
    INDEX
    Explanations

    actions after invocation

    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
     varier
    -0.98
    Sunlight
    -0.94
     FELLOW
    -0.92
     façade
    -0.90
    忙碌
    -0.90
    lieving
    -0.90
     lhes
    -0.87
     convenable
    -0.87
     Oui
    -0.86
     juger
    -0.85
    POSITIVE LOGITS
     before
    1.13
     this
    1.09
     after
    0.98
     on
    0.95
     Before
    0.91
     during
    0.89
     BEFORE
    0.88
    sera
    0.86
     every
    0.85
     even
    0.84
    Activations Density 0.003%

    No Known Activations