© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 179191
    Prev
    Next
    INDEX
    Explanations

    academic literacies

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

    frequency/commonness

    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
    ə
    0.46
    ?
    0.45
    א
    0.44
    Resolved
    0.44
    `
    0.43
    ərd
    0.42
     obliged
    0.42
    మణ
    0.42
    ностей
    0.41
    íme
    0.41
    POSITIVE LOGITS
    𝘄
    0.55
    𝘁
    0.53
     মালিক
    0.51
     ব্যবসা
    0.50
     permitir
    0.50
     প্রযুক্তি
    0.49
     тобто
    0.48
    ừ
    0.48
    techn
    0.47
    barth
    0.46
    Activations Density 0.000%

    No Known Activations