© 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. 64826
    Prev
    Next
    INDEX
    Explanations

    code element definitions

    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
     hadden
    -1.41
     verhind
    -1.34
     quí
    -1.30
     WENT
    -1.27
    hopefully
    -1.27
    anyway
    -1.27
     TÉ
    -1.26
    ܖ
    -1.26
     ſeveral
    -1.25
     intelek
    -1.24
    POSITIVE LOGITS
     not
    1.64
     even
    1.53
     may
    1.39
     is
    1.37
    8
    1.33
     with
    1.31
     almost
    1.24
     appears
    1.21
     seems
    1.21
     includes
    1.20
    Activations Density 0.004%

    No Known Activations