© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 5637
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
     the
    0.46
    ."
    0.43
    ".
    0.42
     oleh
    0.41
     anew
    0.41
    .
    0.41
     memperbaiki
    0.39
     groundbreaking
    0.39
    ),
    0.38
     individual
    0.38
    POSITIVE LOGITS
    俩
    0.48
    would
    0.46
    could
    0.46
    codigo
    0.46
    también
    0.44
    had
    0.43
    canic
    0.42
     would
    0.42
    duled
    0.41
     Органи
    0.40
    Activations Density 0.194%

    No Known Activations