© 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. 396
    Prev
    Next
    INDEX
    Explanations

    sentence structure after "to"

    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
     związ
    0.41
     and
    0.40
    攽
    0.36
     `>`,
    0.36
    憊
    0.36
    䉍
    0.35
    戤
    0.35
    檚
    0.35
    㝅
    0.35
    䅡
    0.35
    POSITIVE LOGITS
    ר
    0.66
    و
    0.66
     a
    0.63
    an
    0.59
    .
    0.58
    ע
    0.58
    ла
    0.57
    -
    0.56
    ي
    0.53
    at
    0.52
    Activations Density 0.050%

    No Known Activations