© 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. 183382
    Prev
    Next
    INDEX
    Explanations

    Friday, God, OS

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

    speaking foreign languages

    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
    0.63
    >
    0.47
    blum
    0.45
    )#
    0.45
    mathrm
    0.43
    markers
    0.43
     Head
    0.42
    feast
    0.42
    marking
    0.42
    leading
    0.41
    POSITIVE LOGITS
    િયો
    0.51
    水を
    0.49
    ጸ
    0.49
     faccia
    0.49
     tới
    0.48
    на
    0.47
     moistened
    0.47
     تھی
    0.47
     Якщо
    0.47
     coseno
    0.46
    Activations Density 0.001%

    No Known Activations