© 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. 37485
    Prev
    Next
    INDEX
    Explanations

    outro texts

    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
     antler
    0.56
    <h2>
    0.55
    <h3>
    0.53
     ankle
    0.51
    ↵
    0.49
    ↵↵
    0.47
     unscathed
    0.46
    ↵↵↵↵↵
    0.45
     hiss
    0.45
     assailant
    0.44
    POSITIVE LOGITS
     लिया
    0.38
     Priorities
    0.37
     Busy
    0.36
    excluded
    0.36
    นิด
    0.36
     Duties
    0.35
    ଦ
    0.35
    що
    0.35
    ціона
    0.35
    煥
    0.35
    Activations Density 0.001%

    No Known Activations