© 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. 221359
    Prev
    Next
    INDEX
    Explanations

    B1G1 or b2b abbreviations

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

    B switch or notation

    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
    冽
    0.45
    ⑦
    0.44
    ↵
    0.42
    ization
    0.42
    ização
    0.40
     Records
    0.39
    諮
    0.38
    ჩევ
    0.38
    точные
    0.37
    知識
    0.37
    POSITIVE LOGITS
     B
    0.79
    B
    0.78
    b
    0.74
    Ｂ
    0.73
     b
    0.68
    ب
    0.65
     bungee
    0.63
    ｂ
    0.61
     บ
    0.61
     Б
    0.60
    Activations Density 0.045%

    No Known Activations