© 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. 8445
    Prev
    Next
    INDEX
    Explanations

    election, Jews, GCD, Jio, sewer

    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
    𝒈
    2.43
    да
    2.38
    きた
    2.23
    𝒎
    2.22
    𝒌
    2.21
    ্ড
    2.09
     זאת
    2.09
     caram
    2.07
    थ
    2.04
     boring
    2.03
    POSITIVE LOGITS
    ে
    3.19
    𝘶
    2.77
    ه
    2.64
    𝘭
    2.57
    ees
    2.48
    ième
    2.47
    र
    2.43
    liness
    2.39
    ن
    2.37
    ان
    2.37
    Activations Density 0.101%

    No Known Activations