© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 186776
    Prev
    Next
    INDEX
    Explanations

    publication date

    np_acts-logits-general · gemini-2.5-flash-lite

    deployment of open

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    from
    0.43
     bedste
    0.42
    ారి
    0.42
     closets
    0.41
    Esta
    0.39
    Companies
    0.39
     enhancers
    0.38
    鷹
    0.38
    particles
    0.38
    Non
    0.37
    POSITIVE LOGITS
    irao
    0.51
     सदर
    0.48
    ตำแหน่ง
    0.48
     शिक्षक
    0.48
     thậm
    0.48
    unteers
    0.47
     શુભેચ્છ
    0.47
     cadast
    0.46
     શિક્ષ
    0.46
     मिलीमीटर
    0.46
    Activations Density 0.000%

    No Known Activations