© 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. 103746
    Prev
    Next
    INDEX
    Explanations

    public static void methods

    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
     erreur
    -1.13
    ньому
    -1.06
     biztons
    -1.05
    先週
    -1.05
     baratas
    -1.02
     bisous
    -1.02
    久し
    -1.02
     astfel
    -1.02
     soyez
    -1.00
     arkas
    -1.00
    POSITIVE LOGITS
     to
    1.78
     when
    1.45
     who
    1.30
    是怎么回事
    1.30
     where
    1.24
     void
    1.23
     ۲۰۰
    1.20
    paedia
    1.19
     whereas
    1.13
    が
    1.12
    Activations Density 0.004%

    No Known Activations