© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 36180
    Prev
    Next
    INDEX
    Explanations

    addressing the user directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ↵
    1.23
     آنها
    1.20
     آن‌ها
    1.18
     他们
    1.12
     estadounidenses
    1.07
    ре
    1.03
     They
    1.02
     parserOptions
    1.02
    ท่องเที่ยว
    0.99
     arouse
    0.99
    POSITIVE LOGITS
    त
    1.25
    ὴν
    1.04
     müşter
    0.96
    y
    0.96
     firmy
    0.95
    hes
    0.95
    fläche
    0.95
    சிரியர்
    0.94
    হ
    0.94
     itibaren
    0.92
    Activations Density 0.073%

    No Known Activations