© 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. 34-GEMMASCOPE-RES-131K
    7. 106747
    Prev
    Next
    INDEX
    Explanations

    minimally invasive, non-invasive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    operable
    -0.86
    minated
    -0.80
    plan
    -0.77
     tư
    -0.77
     Einzel
    -0.74
     やすい
    -0.74
     Doncaster
    -0.74
     accident
    -0.73
    ticular
    -0.71
    rella
    -0.71
    POSITIVE LOGITS
     invasive
    2.80
    invasive
    2.20
     intrusive
    2.17
     Invasive
    2.14
     invasion
    1.67
     invas
    1.60
     Invasion
    1.46
     Intru
    1.46
     intrusion
    1.44
     inva
    1.38
    Activations Density 0.085%

    No Known Activations