© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 60956
    Prev
    Next
    INDEX
    Explanations

    Sections and units

    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_all/layer_41_width_262k_l0_big
    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
    ग्विजय
    0.43
     krok
    0.41
     lấy
    0.40
    judicial
    0.40
    校园
    0.40
     സംഭവ
    0.39
    ரன்
    0.38
    ⵎ
    0.38
     Merc
    0.38
    侩
    0.38
    POSITIVE LOGITS
     Section
    1.10
     section
    0.99
    Section
    0.98
     Subsection
    0.97
     قسم
    0.96
    section
    0.95
     Unit
    0.95
     відді
    0.88
    Subsection
    0.87
     unit
    0.86
    Activations Density 0.002%

    No Known Activations