© 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. 3477
    Prev
    Next
    INDEX
    Explanations

    say, is, decir, bankrupt

    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
     fréquentes
    0.84
    го
    0.83
    い
    0.83
    хода
    0.82
    effective
    0.79
    orrow
    0.79
    𝙚
    0.79
    0.78
    elbe
    0.77
    aptic
    0.76
    POSITIVE LOGITS
     dizer
    1.20
    is
    1.02
     decir
    0.95
     bankrupt
    0.91
     сказать
    0.90
     Aussi
    0.90
     Marxist
    0.88
     anarch
    0.88
     debunk
    0.88
     Согласно
    0.87
    Activations Density 1.123%

    No Known Activations