© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38780
    Prev
    Next
    INDEX
    Explanations

    adverbs qualifying positive attributes

    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
    ícias
    -1.75
     that
    -1.54
     this
    -1.54
    tifiable
    -1.47
    strahlung
    -1.45
     when
    -1.39
    tonsoft
    -1.37
    んだから
    -1.36
    ctomy
    -1.30
    んじゃ
    -1.29
    POSITIVE LOGITS
     yağı
    1.26
     conoci
    1.26
     ayrıca
    1.23
    كويكب
    1.23
    ようです
    1.19
    Œ
    1.19
     tambin
    1.17
     strong
    1.16
     also
    1.16
    ことから
    1.16
    Activations Density 0.090%

    No Known Activations