© 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. 38871
    Prev
    Next
    INDEX
    Explanations

    leaf photosynthesis, piles, springs, extract, spots

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

    references to leaves, especially in botanical or scientific contexts.

    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
    .
    -2.75
     —
    -2.16
    ⡪
    -2.14
     भी
    -2.11
    ”
    -2.03
    ti
    -2.02
    .”
    -2.02
    ’
    -1.92
     avez
    -1.91
    谷川
    -1.91
    POSITIVE LOGITS
    '
    3.56
     '
    2.41
    .''
    2.39
     سامسون
    2.28
     dotyczące
    2.22
    ...?
    2.20
     colaborar
    2.17
     continúas
    2.16
    colgante
    2.14
    krok
    2.14
    Activations Density 0.024%

    No Known Activations