© 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. 128380
    Prev
    Next
    INDEX
    Explanations

    physical marks and damage

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

    The neuron activates on words naming physical traces or surface markings (e.g. scuff marks, circular marks, tracks, rings, craters).

    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
    D
    -1.62
    C
    -1.56
    \
    -1.51
                
    -1.45
    G
    -1.45
    E
    -1.38
    `
    -1.33
    U
    -1.33
    P
    -1.32
    X
    -1.32
    POSITIVE LOGITS
    dámské
    1.67
    Sekarang
    1.59
     škola
    1.59
     estrateg
    1.44
     mentiras
    1.42
     texturas
    1.41
     Eigentü
    1.41
    Tujuan
    1.41
    
    1.40
    servicios
    1.38
    Activations Density 0.036%

    No Known Activations