© 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-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 527
    Prev
    Next
    INDEX
    Explanations

    so followed by pronoun

    np_acts-logits-general · gemini-2.5-flash-lite

    so now, so understanding, so every

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ó
    0.94
     I
    0.73
    in
    0.73
    و
    0.72
    us
    0.71
    and
    0.66
     B
    0.66
    ल
    0.64
     map
    0.64
     sympath
    0.63
    POSITIVE LOGITS
    ان
    0.92
     он
    0.80
     isn
    0.79
    か
    0.76
     an
    0.75
    к
    0.73
     인한
    0.73
    ва
    0.70
     it
    0.70
    an
    0.69
    Activations Density 0.819%

    No Known Activations