© 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. 25744
    Prev
    Next
    INDEX
    Explanations

    comparing and contrasting

    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
     aparatos
    -1.00
     delectable
    -0.98
     masterful
    -0.98
     hefty
    -0.98
     VERY
    -0.96
     molti
    -0.95
     blatant
    -0.93
     whimsical
    -0.92
     sturdy
    -0.91
     boister
    -0.91
    POSITIVE LOGITS
     how
    1.29
     regarding
    1.27
     their
    1.20
     from
    1.17
     out
    1.10
     in
    1.09
     getting
    1.05
     providing
    1.05
     other
    1.00
    Regarding
    0.99
    Activations Density 0.176%

    No Known Activations