© 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. 10-GEMMASCOPE-RES-131K
    7. 104537
    Prev
    Next
    INDEX
    Explanations

    not an expert

    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_10/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
     one
    -1.46
     Dicapai
    -1.38
    ént
    -1.27
     for
    -1.25
    錚
    -1.21
     with
    -1.17
    یشن
    -1.17
     през
    -1.13
    밌
    -1.12
     dám
    -1.09
    POSITIVE LOGITS
     how
    1.49
    U
    1.36
     but
    1.36
     său
    1.30
    enterio
    1.30
     таких
    1.27
     различных
    1.27
     этих
    1.26
    ou
    1.25
     beziehungs
    1.23
    Activations Density 0.050%

    No Known Activations