© 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. 99999
    Prev
    Next
    INDEX
    Explanations

    RuPaul, GTX, VEGF, Fusarium

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

    product names or model numbers, particularly for technology products like GPUs (GTX) and biological factors (VEGF).

    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
    of
    -2.41
    ).
    -2.23
    }$,
    -1.96
     Of
    -1.95
    on
    -1.88
     He
    -1.85
    }$.
    -1.82
    ed
    -1.80
    \
    -1.77
    if
    -1.76
    POSITIVE LOGITS
    蟶
    1.86
    짭
    1.80
     bière
    1.79
    〼
    1.77
    ܧ
    1.75
    뀨
    1.72
    妧
    1.70
    땃
    1.70
     collè
    1.69
     pittores
    1.68
    Activations Density 0.044%

    No Known Activations