© 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. 8567
    Prev
    Next
    INDEX
    Explanations

    features and details

    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
    ે
    1.23
    s
    1.16
    𝑫
    1.02
    𝑮
    1.01
    sburg
    1.01
    ことなく
    0.98
     Перейти
    0.96
    জ্ঞা
    0.96
    न्तर
    0.92
    chromedriver
    0.91
    POSITIVE LOGITS
    й
    1.06
    ので
    1.06
     caut
    1.05
     able
    1.05
     crumbs
    1.04
     sizing
    1.02
     amenities
    1.02
    撾
    1.01
    Á
    1.01
     specifications
    1.01
    Activations Density 0.120%

    No Known Activations