© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12497
    Prev
    Next
    INDEX
    Explanations

    end of sentence or quote

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

    dialogue punctuation context

    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_16k_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
    ехать
    0.44
     значит
    0.44
    ד
    0.44
    趼
    0.43
    璐
    0.42
    дон
    0.41
    提醒
    0.41
     এলাকায়
    0.41
    т
    0.41
     требуют
    0.41
    POSITIVE LOGITS
     shocking
    0.52
     conformément
    0.47
     පිළිබඳ
    0.46
     gemäß
    0.46
     heterogeneity
    0.46
     attitude
    0.45
     supplementary
    0.45
     filial
    0.44
     circost
    0.44
     antidepressant
    0.43
    Activations Density 0.015%

    No Known Activations