© 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. 59979
    Prev
    Next
    INDEX
    Explanations

    support team, TOMAL2, national walking, validated product, platinum credit

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

    heterosexual intercourse or enable heap partner

    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
    ଞ
    0.49
     ءِ
    0.49
    compatibility
    0.49
     возмо
    0.47
     канце
    0.47
     genealogical
    0.47
    qual
    0.46
     ви
    0.46
     мг
    0.46
    yearly
    0.46
    POSITIVE LOGITS
     Chu
    0.52
     Međ
    0.49
     Sek
    0.48
    秀
    0.48
     Romain
    0.46
     Nichols
    0.46
     Ley
    0.46
    īs
    0.46
     Unwin
    0.46
     Slade
    0.45
    Activations Density 0.000%

    No Known Activations