© 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. 93083
    Prev
    Next
    INDEX
    Explanations

    questions starting with really

    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
     PUSTAKA
    -1.27
     spirito
    -1.23
    ък
    -1.16
    گاب
    -1.16
    꽈
    -1.13
    帖最后由
    -1.12
     ако
    -1.12
    LoginComponent
    -1.11
     souverain
    -1.10
     tumultuous
    -1.09
    POSITIVE LOGITS
    ?
    1.37
    如此
    1.19
     which
    1.17
    ”
    1.15
    as
    1.15
    that
    1.15
    Sometimes
    1.14
    Really
    1.13
    そんなに
    1.13
     इत
    1.08
    Activations Density 0.015%

    No Known Activations