© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 104600
    Prev
    Next
    INDEX
    Explanations

    Silver Selfies

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

    following prepositions

    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_31_width_262k_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
    IS
    0.94
    AN
    0.79
    ORE
    0.70
    ।
    0.70
    IN
    0.68
     when
    0.66
    UR
    0.62
    RA
    0.60
    Ö
    0.59
     la
    0.58
    POSITIVE LOGITS
    jenigen
    0.86
    atrical
    0.74
    นี่
    0.72
    ه
    0.64
    zelfde
    0.61
    mselves
    0.60
    지만
    0.59
    sembled
    0.59
    ت
    0.58
    其他
    0.57
    Activations Density 0.160%

    No Known Activations