© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 11227
    Prev
    Next
    INDEX
    Explanations

    specify a time or alternative

    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_22_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
    ছের
    0.67
    ജീവ
    0.66
     Northwest
    0.64
    виа
    0.62
     ಹೋ
    0.62
     기본적인
    0.62
    ികൾ
    0.61
    잼
    0.60
    Ẓ
    0.59
     限定
    0.59
    POSITIVE LOGITS
     timing
    2.99
     Timing
    2.78
     Zeitpunkt
    2.71
     time
    2.71
    Timing
    2.70
     times
    2.64
    タイミング
    2.58
    timing
    2.58
     timings
    2.41
     времени
    2.35
    Activations Density 0.251%

    No Known Activations