© 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. 156660
    Prev
    Next
    INDEX
    Explanations

    save games, aspect ratio

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

    common phrasal continuations

    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
     novi
    0.47
    これまで
    0.45
     पछ
    0.45
     coeur
    0.43
     nuova
    0.43
     முக்கிய
    0.43
     vuole
    0.42
    ٬
    0.42
    今まで
    0.42
     llega
    0.41
    POSITIVE LOGITS
    מ
    0.49
     embank
    0.48
    सिया
    0.44
     drugs
    0.43
     Drugs
    0.43
     painkillers
    0.43
    проек
    0.43
    డంతో
    0.43
     diathermy
    0.43
     takže
    0.42
    Activations Density 0.004%

    No Known Activations