© 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. 44449
    Prev
    Next
    INDEX
    Explanations

    official court documents

    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_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
    2
    -2.69
    3
    -2.66
    0
    -2.66
    a
    -2.58
    9
    -2.53
    1
    -2.50
    which
    -2.41
    ні
    -2.09
     -
    -2.08
    ''
    -2.02
    POSITIVE LOGITS
    岽
    3.08
    ᾐ
    3.05
    鸶
    3.00
    
    2.69
    튿
    2.66
    
    2.58
    汭
    2.47
    quele
    2.47
     také
    2.42
    jacke
    2.42
    Activations Density 0.012%

    No Known Activations