© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76160
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by ' or was

    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_31_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
     being
    0.33
     Cipher
    0.30
    .."
    0.29
    ющей
    0.29
     Mandalorian
    0.28
    被
    0.28
     Marlin
    0.28
    所有
    0.28
    猢
    0.28
    пов
    0.27
    POSITIVE LOGITS
     crédito
    0.31
     mempertahankan
    0.29
     జాగ
    0.28
     öff
    0.28
     świecie
    0.27
    cono
    0.27
    >→</
    0.27
     eliminates
    0.27
     kneel
    0.27
    স্থ
    0.26
    Activations Density 0.004%

    No Known Activations