© 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
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15458
    Prev
    Next
    INDEX
    Explanations

    descriptive elements and metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     attendants
    1.12
    ̝
    1.11
     irrigation
    1.06
     funerals
    1.02
     работников
    1.02
    ۶
    1.02
     экскур
    1.02
    хождение
    1.02
     conferences
    1.01
    朝日
    1.00
    POSITIVE LOGITS
     ज्यामुळे
    0.83
    comend
    0.80
    (
    0.78
    äder
    0.76
    （
    0.74
     zanim
    0.73
     unterschiedlich
    0.73
    ({
    0.73
     łat
    0.73
    แก้ไข
    0.73
    Activations Density 0.000%

    No Known Activations