Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 6491
    Prev
    Next
    INDEX
    Explanations

    various words following "the"

    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
    the
    0.99
    sthe
    0.84
    te
    0.82
    s
    0.81
    m
    0.79
     the
    0.72
     a
    0.71
    n
    0.70
    йки
    0.70
    aient
    0.70
    POSITIVE LOGITS
     Apesar
    0.76
    해서
    0.67
     Поэтому
    0.67
    ইডি
    0.67
     zásobníku
    0.66
    I
    0.66
     будет
    0.66
     možno
    0.65
    ルの
    0.64
    ום
    0.64
    Activations Density 0.847%

    No Known Activations