© 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. 107580
    Prev
    Next
    INDEX
    Explanations

    reporting what was said or concluded

    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
    スタル
    -0.98
    確かに
    -0.95
    Sebelum
    -0.93
    Мария
    -0.93
    Ольга
    -0.92
     описание
    -0.91
     проблема
    -0.90
     indeed
    -0.88
     selben
    -0.88
    ですから
    -0.88
    POSITIVE LOGITS
     said
    2.52
     say
    1.48
     says
    1.34
     noted
    1.23
     believes
    1.19
    say
    1.16
    said
    1.13
     and
    1.06
     feels
    1.06
     indicated
    1.03
    Activations Density 0.016%

    No Known Activations