© 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. 1724
    Prev
    Next
    INDEX
    Explanations

    want, override, looking forward

    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
    oid
    1.19
     ópt
    1.17
    oides
    1.07
    o
    1.07
     unha
    1.05
    نيك
    1.04
    opuerto
    1.00
    ização
    1.00
    oooooooo
    1.00
     alphabet
    0.99
    POSITIVE LOGITS
    ects
    1.18
    insert
    1.18
    ఈ
    1.14
     må
    1.13
    वेंट
    1.11
     norske
    1.10
     enseign
    1.09
    烣
    1.09
    NEEDED
    1.09
    gents
    1.09
    Activations Density 0.000%

    No Known Activations