© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103417
    Prev
    Next
    INDEX
    Explanations

    international text snippets

    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
     at
    -1.64
     being
    -1.47
     with
    -1.47
     using
    -1.45
     by
    -1.44
     in
    -1.43
     of
    -1.38
     from
    -1.36
     on
    -1.23
     or
    -1.20
    POSITIVE LOGITS
     extré
    1.36
     étoient
    1.34
    greja
    1.34
    และ
    1.30
     réfrig
    1.23
     objectifs
    1.23
     roulant
    1.22
    hich
    1.20
     struktur
    1.19
    derry
    1.19
    Activations Density 0.000%

    No Known Activations