© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 166715
    Prev
    Next
    INDEX
    Explanations

    pronouns in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_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
    芡
    0.40
    ভর
    0.38
    icheskoj
    0.37
    􀂃
    0.36
    LABEL
    0.36
     ideale
    0.35
    [:
    0.34
     njegove
    0.34
     ideales
    0.33
     विक्रय
    0.33
    POSITIVE LOGITS
     him
    0.63
    佢
    0.55
     তিনিই
    0.54
     mình
    0.52
     me
    0.51
    自分
    0.51
     myself
    0.47
     nosotros
    0.46
     they
    0.46
    他是
    0.46
    Activations Density 0.030%

    No Known Activations