© 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. 162900
    Prev
    Next
    INDEX
    Explanations

    change in country or specific location

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

    confirming understanding

    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
     สง
    0.46
    ไฟล์
    0.46
     clavier
    0.45
    ת
    0.45
     esf
    0.44
     cardiac
    0.44
     cabinet
    0.43
    USES
    0.42
     naval
    0.42
     feedwater
    0.42
    POSITIVE LOGITS
    llen
    0.44
     كلم
    0.44
    に向け
    0.43
    Diffusion
    0.43
    骁
    0.42
    ṓ
    0.42
    ုံ
    0.41
    疫情防控
    0.41
    Kron
    0.41
    वासियों
    0.39
    Activations Density 0.002%

    No Known Activations