© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11973
    Prev
    Next
    INDEX
    Explanations

    hit followed by preposition or pronoun

    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
    Negative Logits
    t
    3.56
    d
    2.63
    y
    2.55
    ture
    2.31
    ک
    2.31
    ம்
    2.28
    tional
    2.22
    s
    2.19
    tR
    2.14
    sacrifice
    2.14
    POSITIVE LOGITS
    ྥ
    2.06
    एस
    1.83
    𝘽
    1.81
    𝕕
    1.77
    gerald
    1.70
    الوجی
    1.64
    Diaz
    1.63
    ᾷ
    1.61
    繊
    1.60
    ﾞ
    1.59
    Activations Density 0.011%

    No Known Activations