© 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. 10-GEMMASCOPE-RES-131K
    7. 13368
    Prev
    Next
    INDEX
    Explanations

    method or opportunity

    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
     there
    -2.38
     their
    -1.82
     a
    -1.77
     it
    -1.67
     your
    -1.59
     these
    -1.40
     said
    -1.36
     doing
    -1.34
    there
    -1.25
     там
    -1.25
    POSITIVE LOGITS
     kampen
    1.38
     niektor
    1.34
     voľ
    1.34
     tři
    1.33
    几乎
    1.33
     navnet
    1.30
    甚至
    1.29
    地看着
    1.28
    Así
    1.27
     puisque
    1.27
    Activations Density 0.081%

    No Known Activations