© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 27291
    Prev
    Next
    INDEX
    Explanations

    Grant, Age, Group, Direct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Magical
    0.43
    ็อก
    0.39
    د
    0.39
     Diagnose
    0.38
    YouTube
    0.38
     Sergio
    0.38
     Sasha
    0.38
    JECTION
    0.38
     irr
    0.37
     Mario
    0.37
    POSITIVE LOGITS
     utilised
    0.43
    ાર્થના
    0.43
     pretended
    0.42
     lactate
    0.41
    ?,?,
    0.41
     използва
    0.40
     obliterated
    0.40
    鐒
    0.40
     канцеля
    0.39
     লিমি
    0.39
    Activations Density 0.001%

    No Known Activations