© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77206
    Prev
    Next
    INDEX
    Explanations

    aggravated crimes and software licenses

    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
    Micros
    -0.84
    mains
    -0.76
    ToOne
    -0.75
    Beijinhos
    -0.75
     MainAxisSize
    -0.73
     Muhamma
    -0.73
     Micros
    -0.72
     पढ़
    -0.72
    ленно
    -0.71
    beschreibung
    -0.71
    POSITIVE LOGITS
     Agatha
    0.68
    ented
    0.67
     Hum
    0.66
    klen
    0.66
     Ap
    0.65
     Marc
    0.65
    vgg
    0.65
    Nec
    0.64
     rescued
    0.62
    連携
    0.61
    Activations Density 0.078%

    No Known Activations