© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71494
    Prev
    Next
    INDEX
    Explanations

    citation markers

    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
     even
    -1.69
     with
    -1.60
     in
    -1.57
     only
    -1.55
     of
    -1.38
     at
    -1.38
     just
    -1.35
     which
    -1.31
     ONLY
    -1.29
     battling
    -1.26
    POSITIVE LOGITS
     and
    2.08
     vijf
    1.45
     Dinas
    1.34
     zeven
    1.34
     frequentemente
    1.30
     verschillende
    1.27
     EIGHT
    1.26
     både
    1.25
    jourd
    1.23
     greek
    1.23
    Activations Density 0.043%

    No Known Activations