© 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-16K
    7. 4562
    Prev
    Next
    INDEX
    Explanations

    conversational language

    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_16k_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
    א
    1.41
    𝖐
    1.34
    dır
    1.32
    ﻜ
    1.31
    us
    1.30
    rific
    1.30
    ból
    1.28
    THING
    1.28
    ق
    1.28
    ب
    1.27
    POSITIVE LOGITS
    ि
    1.30
    ور
    1.16
    स्पति
    1.00
     toluene
    0.98
     leukocyte
    0.98
    ية
    0.97
     від
    0.95
    杮
    0.95
    地铁
    0.93
    де
    0.92
    Activations Density 0.366%

    No Known Activations