© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1717
    Prev
    Next
    INDEX
    Explanations

    possessive 's' followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    м
    2.70
    ed
    2.36
    er
    2.35
    ה
    2.27
    ing
    2.26
    л
    2.11
    д
    2.09
    y
    2.04
    에
    2.02
    e
    2.02
    POSITIVE LOGITS
     Sake
    2.22
     vacated
    1.79
     sake
    1.79
    urf
    1.76
    omeness
    1.69
     Hole
    1.68
     finest
    1.68
     男性用
    1.64
    ildenafil
    1.61
    ృష్టి
    1.60
    Activations Density 0.366%

    No Known Activations