© 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. 72073
    Prev
    Next
    INDEX
    Explanations

    technical and medical descriptors

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

    technical or specialized adjectives that describe a subject's nature or properties.

    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
     zowel
    -1.18
     både
    -0.94
     richting
    -0.93
     wszyst
    -0.92
    multer
    -0.90
     äußerst
    -0.89
     "'";
    -0.88
     AUSSI
    -0.87
     iedere
    -0.87
     halben
    -0.86
    POSITIVE LOGITS
     minne
    1.00
     furia
    0.96
     brune
    0.89
    」
    0.89
     ferie
    0.89
    ваги
    0.88
     diabetic
    0.87
     другие
    0.87
     equivalent
    0.87
    rage
    0.86
    Activations Density 0.088%

    No Known Activations