© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84687
    Prev
    Next
    INDEX
    Explanations

    legal charges and court proceedings

    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
    蒻
    -0.80
    sku
    -0.76
    ochlor
    -0.76
    rien
    -0.75
     socializing
    -0.74
     komun
    -0.74
     Jaroslav
    -0.73
     гаранти
    -0.71
     showers
    -0.70
    rapport
    -0.70
    POSITIVE LOGITS
     sections
    0.86
    (&_
    0.85
     penal
    0.83
     Arms
    0.82
    entamiento
    0.82
    inté
    0.78
     punishable
    0.75
     Sections
    0.75
     relevant
    0.75
     but
    0.74
    Activations Density 0.007%

    No Known Activations