© 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. 459
    Prev
    Next
    INDEX
    Explanations

    hexadecimal identifiers

    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
    ...");
    0.51
     ähm
    0.51
     })_{
    0.50
    `-
    0.49
    ...")
    0.48
    ・・・。
    0.47
     conspiring
    0.45
     veramente
    0.44
    ondere
    0.44
    ...\...\...\...\
    0.44
    POSITIVE LOGITS
     volcano
    0.53
    口
    0.51
    ⚭
    0.49
    VT
    0.47
    佞
    0.47
     baggage
    0.46
     volcanic
    0.46
    urgence
    0.46
    affee
    0.46
     brings
    0.46
    Activations Density 0.001%

    No Known Activations