© 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. 5054
    Prev
    Next
    INDEX
    Explanations

    ammonium nitrate, hardware, chef strategy

    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
    بك
    1.27
    Inbox
    1.26
    ب
    1.22
    u
    1.17
    y
    1.11
    moved
    1.10
    بول
    1.08
    al
    1.07
    swiss
    1.06
    entered
    1.05
    POSITIVE LOGITS
    ધી
    1.23
     ost
    1.13
    據
    1.13
     gelegen
    1.10
    畔
    1.06
    َ
    1.05
     aqu
    1.04
    果
    1.04
    が一
    1.04
     scripts
    1.03
    Activations Density 0.000%

    No Known Activations