© 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. 26208
    Prev
    Next
    INDEX
    Explanations

    effects of medical conditions

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

    technical or programming language elements in text.

    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
    corer
    -1.16
    InSection
    -1.13
    chage
    -1.11
    pleft
    -1.09
    timg
    -1.08
    ToBounds
    -1.08
     glyphicon
    -1.07
    OnInit
    -1.05
    OrNil
    -1.05
    кура
    -1.03
    POSITIVE LOGITS
     those
    1.22
     halted
    1.16
    —(
    1.10
     findings
    1.08
    が可能
    1.07
    diğinde
    1.07
     increased
    1.05
     with
    1.02
    ėjimas
    1.00
     these
    1.00
    Activations Density 0.000%

    No Known Activations