© 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. 85120
    Prev
    Next
    INDEX
    Explanations

    ocular and binocular vision

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

    terms related to optical devices and eye anatomy, such as "binoculars" and "ocular".

    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
    ﮩ
    -2.86
     или
    -2.23
    ⇰
    -2.17
    砹
    -2.13
     Many
    -2.02
    戗
    -1.95
     sebagian
    -1.95
     Of
    -1.93
    楙
    -1.90
     Which
    -1.89
    POSITIVE LOGITS
    8
    2.28
    5
    2.03
    .
    1.98
    \
    1.85
    4
    1.85
    ها
    1.83
    性命
    1.80
    6
    1.80
     erwerben
    1.77
    随后
    1.76
    Activations Density 0.004%

    No Known Activations