© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65127
    Prev
    Next
    INDEX
    Explanations

    prime, composite, number

    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
     muñeca
    -1.13
     navideña
    -1.11
     recupera
    -1.01
    Makanan
    -1.01
     durante
    -1.00
    ⏑
    -0.96
     enfati
    -0.96
    ፖ
    -0.96
     dönüş
    -0.94
    område
    -0.93
    POSITIVE LOGITS
     because
    1.36
     although
    1.31
     but
    1.27
     after
    1.23
     had
    1.22
     as
    1.21
     with
    1.20
     by
    1.16
     increased
    1.14
     or
    1.10
    Activations Density 0.004%

    No Known Activations