© 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. 34-GEMMASCOPE-RES-131K
    7. 87225
    Prev
    Next
    INDEX
    Explanations

    find anything anywhere

    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_34/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
     alcuni
    -1.21
     بعض
    -1.17
     некото
    -1.16
    pięk
    -1.16
     alcune
    -1.15
     berbagai
    -1.09
    さり
    -1.03
     ſel
    -1.03
     certains
    -1.02
    jsxFileName
    -1.02
    POSITIVE LOGITS
     any
    3.44
     anything
    2.73
     anyone
    2.25
     anywhere
    2.06
    任何
    2.00
     where
    1.98
     or
    1.70
    有任何
    1.69
     anybody
    1.68
     anymore
    1.66
    Activations Density 0.073%

    No Known Activations