© 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. 4294
    Prev
    Next
    INDEX
    Explanations

    printing, eat, sell

    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
    ة
    0.73
    ן
    0.71
    ↵
    0.59
    ја
    0.58
    ing
    0.54
    us
    0.54
    ut
    0.52
    ode
    0.52
    ە
    0.52
    ፣
    0.52
    POSITIVE LOGITS
    𝙜
    0.62
    with
    0.61
    {
    0.60
    𝘨
    0.56
    萸
    0.56
    лета
    0.55
    shirts
    0.54
     menikah
    0.54
    the
    0.54
    起来
    0.54
    Activations Density 0.473%

    No Known Activations