© 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. 15349
    Prev
    Next
    INDEX
    Explanations

    draw bounding boxes

    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
    etsch
    1.02
    reciation
    1.02
    :$
    0.94
     vec
    0.94
    y
    0.92
    ecture
    0.92
    лығы
    0.92
    tive
    0.89
    Else
    0.89
    ᅭ
    0.89
    POSITIVE LOGITS
     acuity
    1.06
     cardiomy
    1.04
     acc
    1.04
     anger
    1.03
     uncontroll
    1.01
     goble
    1.00
    kä
    0.99
     HeLa
    0.99
     cheeks
    0.95
    ून
    0.94
    Activations Density 0.001%

    No Known Activations