© 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-16K
    7. 152
    Prev
    Next
    INDEX
    Explanations

    thinking about steps

    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_16k_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
    써
    1.68
    서
    1.59
    an
    1.58
    我覺得
    1.50
    к
    1.36
    cı
    1.36
    我认为
    1.33
    re
    1.32
    我觉得
    1.30
    서를
    1.29
    POSITIVE LOGITS
     aloud
    1.74
    ရှား
    1.62
    n
    1.47
    tat
    1.43
    LinkedList
    1.42
    t
    1.38
     safest
    1.36
     Secretario
    1.36
    TypeOf
    1.36
    nial
    1.34
    Activations Density 0.989%

    No Known Activations