© 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. 31286
    Prev
    Next
    INDEX
    Explanations

    plant types with a

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

    descriptions of plants, particularly when describing their physical characteristics.

    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
    ⓕ
    -0.76
    movq
    -0.70
    encoded
    -0.69
    IS
    -0.68
     sadece
    -0.67
    嘴唇
    -0.67
    XT
    -0.66
    フル
    -0.66
     quartered
    -0.65
    已经
    -0.64
    POSITIVE LOGITS
     annual
    1.25
     perennial
    1.21
     biennial
    1.10
     herbs
    1.00
     herbaceous
    1.00
     Annual
    1.00
     upright
    0.94
    Annual
    0.94
    altezza
    0.94
    annual
    0.93
    Activations Density 0.050%

    No Known Activations