© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9043
    Prev
    Next
    INDEX
    Explanations

    wall

    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
    स्ट
    3.12
    ї
    2.71
    ฀
    2.63
    ferencia
    2.53
    elast
    2.48
    roleum
    2.47
    와
    2.47
    繹
    2.40
    आर
    2.39
    ς
    2.35
    POSITIVE LOGITS
    ्यूम
    4.55
    ла
    3.83
    ن
    3.63
    jasper
    3.42
    м
    3.38
    不住
    3.04
    ル
    3.03
    papers
    3.02
     perpetrated
    2.88
    드
    2.86
    Activations Density 0.026%

    No Known Activations