© 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. 54437
    Prev
    Next
    INDEX
    Explanations

    names often starting with Paw, Vat, Post, 1, Woman

    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
     their
    -1.74
     they
    -1.52
     all
    -1.47
     faut
    -1.09
     who
    -1.09
     been
    -1.08
     just
    -1.02
     this
    -1.02
     for
    -1.01
     before
    -1.00
    POSITIVE LOGITS
    Reklama
    1.34
     články
    1.27
    Mange
    1.23
    Fourni
    1.20
    exprimer
    1.19
    postfix
    1.18
    Charakter
    1.18
    Preparazione
    1.17
    Encontra
    1.16
    Aç
    1.16
    Activations Density 0.000%

    No Known Activations