© 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. 132508
    Prev
    Next
    INDEX
    Explanations

    pronouns and accepted phrases

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

    practices, reasons, exploring

    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
    t
    0.55
    т
    0.49
    Sm
    0.49
    Референ
    0.49
    Abbreviations
    0.49
    Ah
    0.48
    quando
    0.48
     शहीद
    0.48
    𝙧
    0.47
    姒
    0.46
    POSITIVE LOGITS
     ba
    0.53
     aim
    0.48
     specialize
    0.47
     manus
    0.46
     corporation
    0.46
     نقدم
    0.45
     nabí
    0.45
     shelters
    0.45
     conduct
    0.45
     promete
    0.45
    Activations Density 0.002%

    No Known Activations