© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 66580
    Prev
    Next
    INDEX
    Explanations

    numbers and building status

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

    kotlin import androidx.activity

    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
     ergonomics
    0.48
    EN
    0.46
    গরের
    0.46
    創建
    0.45
    𝗣
    0.45
    Mathemat
    0.45
    TAX
    0.45
    TON
    0.44
     ئەم
    0.44
    Whitelist
    0.44
    POSITIVE LOGITS
    under
    0.48
     ثلاثة
    0.47
    ajara
    0.43
    iii
    0.42
     ഗ
    0.42
     الصل
    0.42
    three
    0.42
     ured
    0.42
     trei
    0.41
    upa
    0.41
    Activations Density 0.000%

    No Known Activations