© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 150717
    Prev
    Next
    INDEX
    Explanations

    it (pronoun)

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_width_262k_l0_small_affine
    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
    Ive
    0.38
    In
    0.36
    ways
    0.36
    ated
    0.35
    istics
    0.35
    Not
    0.35
    ))],
    0.34
    nament
    0.34
    Suddenly
    0.34
    rightsquigarrow
    0.34
    POSITIVE LOGITS
     it
    1.92
    它
    1.48
    มัน
    1.20
     它
    1.17
    ມັນ
    1.13
    它是
    1.05
     มัน
    1.02
     оно
    0.99
    វា
    0.98
     វា
    0.98
    Activations Density 0.001%

    No Known Activations