© 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
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14363
    Prev
    Next
    INDEX
    Explanations

    Excited about future prospects

    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
    ⎯
    1.41
    ю
    1.40
    iseconds
    1.36
     społecz
    1.32
    Alcohol
    1.31
     irradiance
    1.28
    р
    1.27
     seva
    1.25
    ت
    1.21
     ситуацию
    1.20
    POSITIVE LOGITS
     prospect
    1.55
     prospects
    1.41
    𝗹
    1.39
    antic
    1.34
    le
    1.33
    ຕົ
    1.29
     darum
    1.25
     logro
    1.25
    ло
    1.24
     나머지
    1.24
    Activations Density 0.021%

    No Known Activations