© 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. 64762
    Prev
    Next
    INDEX
    Explanations

    This X [verb]

    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
     and
    -1.39
     from
    -1.30
     it
    -1.20
     his
    -1.13
     out
    -1.11
    bės
    -1.04
     its
    -1.02
    keted
    -1.01
     or
    -1.00
     this
    -0.97
    POSITIVE LOGITS
     also
    1.91
     then
    1.55
     however
    1.30
     will
    1.29
     atunci
    1.27
     també
    1.21
     can
    1.18
     bukanlah
    1.15
    However
    1.15
     também
    1.11
    Activations Density 0.071%

    No Known Activations