© 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. 70261
    Prev
    Next
    INDEX
    Explanations

    tango shows

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

    used in context

    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
     Spacious
    0.50
     नग
    0.48
     ചെയ്യുന്നത്
    0.48
     หาก
    0.47
     व
    0.46
     यदि
    0.45
    യ്‌
    0.45
     Parties
    0.44
     ("
    0.44
     слай
    0.43
    POSITIVE LOGITS
     potatoes
    0.51
    ethash
    0.50
    チーズ
    0.48
    شي
    0.48
    ζε
    0.48
    识
    0.47
    ヒ
    0.47
    хи
    0.47
    нее
    0.46
     olive
    0.46
    Activations Density 0.000%

    No Known Activations