© 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. 64758
    Prev
    Next
    INDEX
    Explanations

    report, data, skills, contracts

    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
    took
    -1.30
    Called
    -1.20
    showed
    -1.18
    去
    -1.18
     constituted
    -1.17
    conducted
    -1.15
     undertook
    -1.13
    Served
    -1.11
     Took
    -1.09
    offered
    -1.07
    POSITIVE LOGITS
     that
    2.67
     που
    1.53
     which
    1.53
     previously
    1.32
    ที่
    1.22
     التي
    1.18
     שה
    1.13
    齟
    1.10
     الذي
    1.09
     ранее
    1.05
    Activations Density 0.524%

    No Known Activations