© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9675
    Prev
    Next
    INDEX
    Explanations

    list item separation

    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
     of
    -1.66
     in
    -1.27
     it
    -1.25
     when
    -1.22
     not
    -1.19
     It
    -1.16
     B
    -1.15
     If
    -1.13
     This
    -1.13
    づけ
    -1.10
    POSITIVE LOGITS
    archical
    1.34
     diriger
    1.30
    なども
    1.24
    などが
    1.23
    uded
    1.23
    も多く
    1.21
    などを
    1.20
    乁
    1.20
     FORCES
    1.20
    もありますが
    1.17
    Activations Density 0.039%

    No Known Activations