© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8487
    Prev
    Next
    INDEX
    Explanations

    `[` and `Next Generation`

    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
    ので
    1.46
    து
    1.40
    종
    1.37
    ção
    1.33
    ung
    1.33
    fact
    1.31
     possa
    1.29
    طب
    1.28
    จะต้อง
    1.28
     pueda
    1.28
    POSITIVE LOGITS
    ྙ
    1.63
    بار
    1.62
     hampers
    1.57
    ekkür
    1.56
    szer
    1.49
    рного
    1.42
     cardia
    1.40
    আমাদের
    1.40
     excitatory
    1.37
     છીએ
    1.32
    Activations Density 0.000%

    No Known Activations