© 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. 126115
    Prev
    Next
    INDEX
    Explanations

    picks up, belief that, Then I

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

    visual approach

    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
     приобре
    0.50
     PAINT
    0.48
     হেতু
    0.47
    選
    0.46
     курс
    0.46
     fixtures
    0.45
     кори
    0.45
    閥
    0.43
     fixture
    0.42
     આમંત્રણ
    0.42
    POSITIVE LOGITS
    na
    0.49
    cud
    0.48
    ffmpeg
    0.46
    ാൻ
    0.46
    琀
    0.43
    ⏱
    0.43
     empat
    0.43
    চ্ছন্দ
    0.42
    lden
    0.42
    empat
    0.42
    Activations Density 0.001%

    No Known Activations