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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 8529
    Prev
    Next
    INDEX
    Explanations

    for just

    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_9_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
     mellitus
    1.04
    x
    1.02
     može
    1.02
    <0xF3>
    1.00
    0
    1.00
    k
    0.99
     puoi
    0.96
    1
    0.94
    w
    0.94
     adatto
    0.93
    POSITIVE LOGITS
     the
    1.59
     ihe
    1.32
     các
    1.13
     those
    1.12
     שה
    1.09
     ‘‘
    1.09
     thoſe
    1.07
     việc
    1.06
     AML
    1.04
     quarterbacks
    1.03
    Activations Density 3.910%

    No Known Activations