© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126772
    Prev
    Next
    INDEX
    Explanations

    specific word pairings

    np_acts-logits-general · gemini-2.5-flash-lite

    meme, button, improves, labels, demand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ह
    0.47
     Kel
    0.44
    ම්භ
    0.44
     variations
    0.43
    Kel
    0.41
     कं
    0.41
     Hagan
    0.41
     kel
    0.41
    elesaian
    0.41
    堀
    0.41
    POSITIVE LOGITS
    ша
    0.50
    ्युनिटी
    0.49
    reportBody
    0.48
    通販
    0.47
    тони
    0.47
    umbnail
    0.46
     पूजन
    0.46
    ردم
    0.45
    фект
    0.45
     थांब
    0.45
    Activations Density 0.000%

    No Known Activations