© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26612
    Prev
    Next
    INDEX
    Explanations

    medical kits and supplies

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

    physical tools, supplies, and materials used in DIY, hardware, and technical projects.

    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
    hline
    -1.45
     only
    -1.40
     there
    -1.34
     at
    -1.25
     directly
    -1.24
     even
    -1.15
     it
    -1.12
    iziert
    -1.12
     bezpośrednio
    -1.10
     through
    -1.09
    POSITIVE LOGITS
    用来
    1.46
    zufügen
    1.14
     två
    1.13
    戕
    1.10
    หรับ
    1.10
    comfortable
    1.09
    wyżs
    1.09
    zaamheid
    1.09
     ausreichend
    1.07
     for
    1.06
    Activations Density 0.024%

    No Known Activations