© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8489
    Prev
    Next
    INDEX
    Explanations

    its core

    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
    ™.
    1.28
    }{
    1.20
    }.
    1.17
    `.
    1.15
    ’.
    1.15
    ᆹ
    1.12
    .…
    1.11
    Another
    1.10
     கூடிய
    1.10
    ².
    1.10
    POSITIVE LOGITS
     cri
    1.20
     December
    1.19
     entanto
    1.17
     comparação
    1.16
     raged
    1.15
     meantime
    1.14
     February
    1.10
     före
    1.09
     هذه
    1.09
     diesem
    1.09
    Activations Density 0.182%

    No Known Activations