© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9450
    Prev
    Next
    INDEX
    Explanations

    contrast or distinction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    fontenc
    1.47
    ̸
    1.36
     igualmente
    1.31
    новременно
    1.31
    ަލ
    1.30
    াল
    1.29
    FileAlignment
    1.27
    ackbar
    1.26
     httpServer
    1.23
    कर्षण
    1.22
    POSITIVE LOGITS
    e
    1.17
    Sob
    1.17
    hood
    1.10
    uning
    1.08
    dest
    1.05
    तम
    1.05
     ion
    1.04
    det
    1.00
    چه
    1.00
    べき
    0.99
    Activations Density 0.014%

    No Known Activations