© 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. 129675
    Prev
    Next
    INDEX
    Explanations

    abandonar, indefinitely, moist soil, hill

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

    infinite loops and recursion

    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
    થી
    0.50
     cient
    0.47
     १२
    0.47
     statistical
    0.46
    AMA
    0.44
     by
    0.44
     متنوع
    0.44
    EN
    0.44
     flats
    0.44
    て
    0.44
    POSITIVE LOGITS
    IServerGame
    0.46
    放弃
    0.46
    Zombie
    0.42
    MatContext
    0.42
    возможно
    0.42
     abandonar
    0.42
     reconciled
    0.41
    osamente
    0.41
    பாளையம்
    0.41
    Venezuela
    0.41
    Activations Density 0.002%

    No Known Activations