© 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. 70628
    Prev
    Next
    INDEX
    Explanations

    photos or pictures

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

    The neuron activates on words referring to visual media (e.g. picture, photo, image, pics).

    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
     with
    -1.84
    也
    -1.64
    U
    -1.52
    As
    -1.50
    AR
    -1.48
    IA
    -1.47
    AS
    -1.47
     &
    -1.46
    也不
    -1.46
    6
    -1.45
    POSITIVE LOGITS
     prized
    1.71
    葶
    1.68
    ⽂
    1.66
    adds
    1.64
    䛗
    1.59
    賸
    1.56
    erschied
    1.55
     啦
    1.55
    yields
    1.55
    祧
    1.52
    Activations Density 0.143%

    No Known Activations