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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 29036
    Prev
    Next
    INDEX
    Explanations

    person pronouns and postpositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    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
    اصيل
    0.77
    atot
    0.72
     Ablauf
    0.71
     contraste
    0.71
     ['(?
    0.71
    ఫ
    0.70
    كين
    0.70
     సినిమాలు
    0.70
    ar
    0.68
     ట
    0.68
    POSITIVE LOGITS
    Medieval
    0.83
    ;
    0.83
    কে
    0.83
     as
    0.82
    ї
    0.82
    ளும்
    0.80
     Medieval
    0.80
    -
    0.80
    ล
    0.79
    Drug
    0.73
    Activations Density 0.011%

    No Known Activations