© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 534
    Prev
    Next
    INDEX
    Explanations

    and or leading to result

    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_17_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
    :
    1.46
     And
    1.16
    And
    1.12
    But
    1.10
     and
    1.09
    ;
    1.07
    .:
    1.05
    A
    1.05
    Both
    1.05
    This
    1.03
    POSITIVE LOGITS
     ultimately
    1.81
     whatnot
    1.80
     consequently
    1.73
     therefor
    1.69
     therefore
    1.65
     hatta
    1.62
     hopefully
    1.57
     subsequently
    1.57
     oftentimes
    1.56
     frankly
    1.54
    Activations Density 3.037%

    No Known Activations