© 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. 93350
    Prev
    Next
    INDEX
    Explanations

    parenthetical explanations

    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
     and
    -2.25
     from
    -1.53
     —
    -1.41
     with
    -1.38
    :
    -1.34
     which
    -1.20
     marvellous
    -1.10
     first
    -1.08
     וכן
    -1.06
     believes
    -1.05
    POSITIVE LOGITS
     ۱۳۹
    1.55
     helft
    1.55
     saludable
    1.49
     conferir
    1.48
     they
    1.48
     pantolon
    1.43
    графия
    1.39
     样
    1.38
     enkelte
    1.36
     <",
    1.34
    Activations Density 0.013%

    No Known Activations