© 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. 146331
    Prev
    Next
    INDEX
    Explanations

    business and technical content

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

    key: description, definition, specification

    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
    অল
    0.47
    뻑
    0.45
     তাল
    0.43
    掏
    0.42
     விழுப்புரம்
    0.42
     ৪০০
    0.42
    olf
    0.42
     आर्यन
    0.42
    গাঁ
    0.41
    慄
    0.41
    POSITIVE LOGITS
     terrorism
    0.50
     terrorist
    0.48
     clair
    0.46
    ਐ
    0.45
    ینہ
    0.45
     testa
    0.45
     funer
    0.45
    works
    0.44
    лка
    0.42
     ریاضی
    0.42
    Activations Density 0.000%

    No Known Activations