© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 167928
    Prev
    Next
    INDEX
    Explanations

    possessive words (my, its)

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

    affects animal respiration

    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
    Negative Logits
    Squares
    0.51
     verdadera
    0.50
    ঙ্গা
    0.50
    ्यूड
    0.48
    רג
    0.48
    <unused82>
    0.46
     komunitas
    0.45
    deleg
    0.45
    routers
    0.45
    sal
    0.45
    POSITIVE LOGITS
     have
    0.50
     chance
    0.46
     հ
    0.44
     an
    0.44
     Madsen
    0.43
    ates
    0.43
     trivially
    0.42
     nemus
    0.42
     PGE
    0.42
     AIR
    0.41
    Activations Density 0.000%

    No Known Activations