© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 203
    Prev
    Next
    INDEX
    Explanations

    has/have followed by verb/noun

    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
    0.62
    筁
    0.62
     và
    0.62
     jakarta
    0.58
    dml
    0.58
    ع
    0.57
    לים
    0.56
    渑
    0.55
    และ
    0.55
     Imagination
    0.54
    POSITIVE LOGITS
    been
    0.80
    speople
    0.71
    are
    0.66
    soldiers
    0.66
     были
    0.64
    an
    0.64
     είχε
    0.64
    hearts
    0.64
    mselves
    0.63
    up
    0.63
    Activations Density 0.375%

    No Known Activations