© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 45002
    Prev
    Next
    INDEX
    Explanations

    frame and framed objects

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

    The neuron fires on occurrences of the word “frame” (or “frames”) in item descriptions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    -1.97
    .
    -1.95
    ㌘
    -1.92
    鹮
    -1.91
     日記
    -1.83
     rollercoaster
    -1.79
     ottima
    -1.79
    7
    -1.73
    5
    -1.71
    only
    -1.63
    POSITIVE LOGITS
     frame
    2.20
    —
    2.02
    ?
    1.91
     Frames
    1.81
     saada
    1.81
     frames
    1.78
     climatic
    1.77
    その他の
    1.76
     Frame
    1.70
    ).
    1.67
    Activations Density 0.014%

    No Known Activations