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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14411
    Prev
    Next
    INDEX
    Explanations

    generated code

    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
    。
    1.45
    .",
    1.44
    ։
    1.43
    :",
    1.41
    。",
    1.31
    。【
    1.30
    。,
    1.30
    ۔
    1.28
    **.
    1.28
    ।
    1.25
    POSITIVE LOGITS
     could
    2.47
     doesn
    2.38
     has
    2.36
     becomes
    2.36
     seems
    2.35
     hasn
    2.33
     cannot
    2.32
     isn
    2.29
     is
    2.29
     might
    2.24
    Activations Density 0.327%

    No Known Activations