© 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. 8707
    Prev
    Next
    INDEX
    Explanations

    machine learning inference

    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
     commutator
    1.55
    ll
    1.43
               
    1.42
    ifiers
    1.39
     pala
    1.37
     começo
    1.36
    lll
    1.36
    戬
    1.35
     writeFile
    1.33
    entityManager
    1.32
    POSITIVE LOGITS
    न
    2.29
    al
    2.14
    an
    2.13
    م
    2.06
    ン
    1.97
    ことなく
    1.88
    र
    1.82
    ن
    1.80
    のは
    1.77
    eel
    1.76
    Activations Density 0.028%

    No Known Activations