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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11348
    Prev
    Next
    INDEX
    Explanations

    complex or bribery

    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
    ンプル
    1.70
     jurors
    1.66
    ర్
    1.62
     excised
    1.61
     debuts
    1.61
    ッチ
    1.58
     divisors
    1.58
    제
    1.58
    neſs
    1.54
     Thereby
    1.53
    POSITIVE LOGITS
    elez
    1.65
    های
    1.56
    います
    1.54
    مة
    1.30
    dos
    1.30
    тной
    1.30
    Et
    1.26
    tub
    1.25
    ps
    1.24
    ke
    1.23
    Activations Density 0.001%

    No Known Activations