© 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. 90691
    Prev
    Next
    INDEX
    Explanations

    names starting with 'Er' or 'Erl'

    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
     Jur
    -0.76
    TOPIC
    -0.74
    cooled
    -0.73
    idp
    -0.72
     circonst
    -0.71
    ]]:
    -0.71
    aggregated
    -0.70
     заду
    -0.69
    (["
    -0.69
    --;
    -0.69
    POSITIVE LOGITS
     закона
    0.79
    过敏
    0.77
     bisexual
    0.73
     家具
    0.71
    referer
    0.68
     instalment
    0.68
    洹
    0.68
     surged
    0.68
    선
    0.68
    长时间
    0.67
    Activations Density 0.035%

    No Known Activations