© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 10669
    Prev
    Next
    INDEX
    Explanations

    under the / this / Section

    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
    CTION
    1.36
    ات
    1.33
    もしくは
    1.31
     nämlich
    1.27
     เด
    1.21
     investigar
    1.21
    दर्शिता
    1.19
    s
    1.19
     قریب
    1.18
    赁
    1.16
    POSITIVE LOGITS
    ার
    1.12
    ন
    1.12
    ור
    1.10
    부터
    1.05
    써
    1.00
    짱
    0.98
    н
    0.95
     Teor
    0.94
    न
    0.94
    emaster
    0.93
    Activations Density 0.002%

    No Known Activations