© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13938
    Prev
    Next
    INDEX
    Explanations

    code execution or questions

    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
     such
    -1.33
    usually
    -1.20
     unn
    -1.16
     فقط
    -1.12
     incluso
    -1.09
    essentially
    -1.09
     повіт
    -1.08
    jue
    -1.08
     usando
    -1.05
     unveils
    -1.05
    POSITIVE LOGITS
     or
    1.74
     as
    1.50
     what
    1.32
     after
    1.31
     Getting
    1.27
    جاب
    1.23
     venturing
    1.20
     getting
    1.19
     severely
    1.18
     classy
    1.17
    Activations Density 0.003%

    No Known Activations