© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15850
    Prev
    Next
    INDEX
    Explanations

    SWIG, IS, Still, CHS, fSWIG, pa, IS, The, Still, CHS, f

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

    The neuron is picking up SWIG interface-file directives (lines beginning with “%” and related SWIG keywords).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ↵↵↵
    -2.11
     =
    -2.00
     в
    -1.64
    //
    -1.57
    ↵↵↵↵
    -1.52
    她就
    -1.51
    7
    -1.48
     involucra
    -1.47
     accessible
    -1.43
    甚至是
    -1.43
    POSITIVE LOGITS
    tembre
    1.81
    筚
    1.61
    ropolitana
    1.59
    LEncoder
    1.58
    ATIONS
    1.51
     fertili
    1.45
     januar
    1.44
    ꈊ
    1.44
    PATIENT
    1.43
    améli
    1.42
    Activations Density 0.004%

    No Known Activations