© 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. 111057
    Prev
    Next
    INDEX
    Explanations

    but, otherwise, other

    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
     jopa
    -1.11
     many
    -0.96
    だけでも
    -0.96
     including
    -0.94
     even
    -0.93
     sogar
    -0.90
     сначала
    -0.89
    Many
    -0.89
     tikai
    -0.88
     only
    -0.88
    POSITIVE LOGITS
     otherwise
    5.16
     other
    4.59
    Otherwise
    4.50
    otherwise
    4.25
     Otherwise
    4.19
     aside
    3.61
     apart
    3.44
    other
    3.38
     OTHERWISE
    3.33
    其他
    3.17
    Activations Density 0.042%

    No Known Activations