© 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. 10-GEMMASCOPE-RES-131K
    7. 70919
    Prev
    Next
    INDEX
    Explanations

    necessity or desirability of use

    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
     of
    -2.00
    hibits
    -1.94
    艄
    -1.83
     mauva
    -1.74
     juſt
    -1.73
     nè
    -1.68
     auffi
    -1.68
    事が
    -1.67
     acheter
    -1.66
     GOtt
    -1.66
    POSITIVE LOGITS
     many
    2.13
     some
    1.89
     any
    1.78
    Many
    1.75
     various
    1.70
     or
    1.69
     and
    1.66
    Some
    1.65
     in
    1.63
     Almost
    1.63
    Activations Density 0.163%

    No Known Activations