© 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. 34-GEMMASCOPE-RES-131K
    7. 92614
    Prev
    Next
    INDEX
    Explanations

    medical and scientific quantities

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

    scientific or academic terms related to measurements, data, or statistics in research papers.

    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_34/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
    sistent
    -1.08
    ⬎
    -1.05
     requiere
    -1.02
    Indien
    -1.00
     dõi
    -0.99
    ześnie
    -0.99
    醐
    -0.99
    Investi
    -0.98
    íté
    -0.97
    ))->
    -0.96
    POSITIVE LOGITS
     is
    3.45
     wynosi
    2.19
     was
    2.09
     varies
    2.08
     exceeds
    1.70
     ranged
    1.68
     equals
    1.63
     составляет
    1.59
     είναι
    1.58
     vary
    1.51
    Activations Density 0.172%

    No Known Activations