© 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. 115461
    Prev
    Next
    INDEX
    Explanations

    unpublished manuscripts

    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
    正好
    -0.75
    IMAL
    -0.74
    away
    -0.71
     internationalen
    -0.71
     and
    -0.68
    tablename
    -0.68
     GBIF
    -0.68
     CSE
    -0.67
     but
    -0.66
    指向
    -0.65
    POSITIVE LOGITS
     manuscript
    2.45
     manuscripts
    2.19
    manus
    1.63
     manuscrit
    1.59
     руко
    1.57
     Manuscript
    1.57
     MS
    1.55
     Manuscripts
    1.52
    Manuscript
    1.49
     manus
    1.45
    Activations Density 0.022%

    No Known Activations