© 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. 196479
    Prev
    Next
    INDEX
    Explanations

    If clauses

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

    consult a healthcare professional

    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
    ០
    0.49
     compagnies
    0.44
    츨
    0.42
    inspired
    0.41
     exploits
    0.41
    ៨
    0.40
    тири
    0.40
    ៤
    0.40
    ੰ
    0.39
    хема
    0.39
    POSITIVE LOGITS
    这点
    0.52
    这一点
    0.49
     Sinon
    0.46
     گذ
    0.43
     nonetheless
    0.43
     Buna
    0.42
     ধৈর্য
    0.42
    也不能
    0.41
     Nonetheless
    0.41
     Außerdem
    0.41
    Activations Density 0.012%

    No Known Activations