© 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. 10-GEMMASCOPE-RES-131K
    7. 43105
    Prev
    Next
    INDEX
    Explanations

    Hanan Shield

    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
    1
    -2.67
    2
    -2.58
    0
    -2.50
    7
    -1.89
    5
    -1.87
    3
    -1.86
    us
    -1.85
    er
    -1.74
    4
    -1.74
     veya
    -1.73
    POSITIVE LOGITS
    欤
    1.86
     '
    1.84
    舠
    1.73
    蠖
    1.63
    UNITIES
    1.56
     ciutat
    1.55
    ustomed
    1.54
    iseaux
    1.54
     Politiker
    1.53
     bukanlah
    1.52
    Activations Density 0.001%

    No Known Activations