© 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. 22-GEMMASCOPE-RES-131K
    7. 69115
    Prev
    Next
    INDEX
    Explanations

    parameter list syntax

    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_22/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
     easier
    -1.33
     which
    -1.32
     who
    -1.30
     one
    -1.30
     that
    -1.29
     fact
    -1.24
     leading
    -1.23
     latter
    -1.22
    ņ
    -1.18
     to
    -1.17
    POSITIVE LOGITS
    Bereits
    1.20
     vorige
    1.18
    了两
    1.18
    ulfon
    1.17
    cuando
    1.17
    ichert
    1.17
     pemberian
    1.16
    你知道
    1.15
    要说
    1.15
     œil
    1.13
    Activations Density 0.007%

    No Known Activations