© 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. 173358
    Prev
    Next
    INDEX
    Explanations

    common english words before other words

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

    non-latin scripts

    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
    emain
    0.55
     putra
    0.50
     स
    0.46
     halaman
    0.46
     selaku
    0.44
     comment
    0.44
    amentos
    0.44
     بذ
    0.43
     alami
    0.43
     lingkaran
    0.43
    POSITIVE LOGITS
    מים
    0.49
    吉
    0.48
    חד
    0.44
    μέν
    0.44
    뻥
    0.44
    ב
    0.41
     যাব
    0.41
    πή
    0.41
     beque
    0.41
    PBC
    0.41
    Activations Density 0.001%

    No Known Activations