© 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. 10-GEMMASCOPE-RES-131K
    7. 128060
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and structures

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

    technical syntax elements in code, formulas, or scientific notation.

    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_10/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
     teeming
    -1.34
     vitally
    -1.34
    Ἴ
    -1.22
     enlightening
    -1.19
     aptly
    -1.18
     ceaseless
    -1.16
     advancing
    -1.16
     escalating
    -1.16
     definitively
    -1.16
     culminating
    -1.15
    POSITIVE LOGITS
     you
    1.10
     or
    1.02
     Then
    1.00
    vacy
    0.97
     demselben
    0.95
    镭
    0.93
     ‘
    0.92
    理
    0.91
    tami
    0.91
     they
    0.91
    Activations Density 24.686%

    No Known Activations