© 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. 12555
    Prev
    Next
    INDEX
    Explanations

    sexual differentiation, numerous methods

    np_acts-logits-general · gemini-2.5-flash-lite

    sports match scores and results, particularly in tennis and other competitive events.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     this
    -1.68
     that
    -1.67
     should
    -1.47
     new
    -1.45
     if
    -1.41
     when
    -1.40
     get
    -1.35
     now
    -1.30
     for
    -1.27
     so
    -1.22
    POSITIVE LOGITS
     betrifft
    1.21
    〬
    1.19
    ܆
    1.19
    Carrito
    1.16
     applau
    1.16
     miroir
    1.16
     verschiedener
    1.15
     spectacular
    1.14
     branco
    1.12
    摇了
    1.11
    Activations Density 0.007%

    No Known Activations