© 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. 22-GEMMASCOPE-2-RES-262K
    7. 20045
    Prev
    Next
    INDEX
    Explanations

    lottery

    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
     keras
    0.81
     нео
    0.78
    блі
    0.77
    bladder
    0.77
    팍
    0.76
    裴
    0.76
    ﺂ
    0.74
    ผ้า
    0.74
    Brandon
    0.74
     நூற்றாண்டின்
    0.74
    POSITIVE LOGITS
    teries
    1.58
    jenigen
    1.09
    ting
    1.07
    tery
    1.04
    ল
    1.00
    TERY
    0.98
    tering
    0.97
     lot
    0.97
    rimazole
    0.92
    ter
    0.88
    Activations Density 0.030%

    No Known Activations