© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 1387
    Prev
    Next
    INDEX
    Explanations

    dark circles, langflow, freemasonry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     and
    0.90
     и
    0.70
     και
    0.67
     và
    0.59
    และ
    0.58
     और
    0.57
     و
    0.55
    和
    0.54
    and
    0.53
     to
    0.51
    POSITIVE LOGITS
     unprecedented
    0.46
    цима
    0.44
    hezza
    0.43
    ھیں
    0.43
     inroads
    0.42
     applaud
    0.40
     voyages
    0.40
     savait
    0.40
    рија
    0.38
     unrival
    0.38
    Activations Density 0.404%

    No Known Activations