© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128250
    Prev
    Next
    INDEX
    Explanations

    special characters and words

    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
     all
    -1.62
     in
    -1.49
     without
    -1.26
     where
    -1.24
     over
    -1.23
     their
    -1.23
     problems
    -1.22
     for
    -1.19
     of
    -1.18
     from
    -1.18
    POSITIVE LOGITS
    fting
    1.31
    痈
    1.11
    感じです
    1.07
     ¬
    1.05
     embaraz
    1.05
    為に
    1.05
    strzy
    1.05
    Hace
    1.04
     necesit
    1.03
     ს
    1.02
    Activations Density 0.000%

    No Known Activations