© 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. 78175
    Prev
    Next
    INDEX
    Explanations

    plant height and cell science

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

    journal or academic publication names like "Plant Cell" and "Food Science".

    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
    rawl
    -0.82
    addImage
    -0.73
    
    -0.73
     mạnh
    -0.72
     ghế
    -0.71
     intimidated
    -0.70
    の中から
    -0.68
     Sme
    -0.68
    packs
    -0.68
     Accumulation
    -0.67
    POSITIVE LOGITS
     competence
    1.24
     competency
    1.07
     subjects
    0.85
     Concurrent
    0.84
     compétence
    0.83
    List
    0.79
    Subjects
    0.76
     Subjects
    0.74
    Compet
    0.73
     sincerity
    0.73
    Activations Density 0.027%

    No Known Activations