© 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. 46114
    Prev
    Next
    INDEX
    Explanations

    knits and purls

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

    Checkpoint Charlie Memorial

    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
     husbands
    0.41
     railroads
    0.41
     पिस्टल
    0.41
     your
    0.41
     this
    0.41
     you
    0.40
    !
    0.40
    expenses
    0.40
     HMRC
    0.40
     (
    0.39
    POSITIVE LOGITS
     예술
    0.47
    ஸ
    0.47
    NoStop
    0.47
     neoplastic
    0.45
    פו
    0.44
    твра
    0.44
     sociocultural
    0.44
    hanahu
    0.43
    Dramatic
    0.43
    ܣ
    0.43
    Activations Density 0.000%

    No Known Activations