© 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. 159731
    Prev
    Next
    INDEX
    Explanations

    measurement, boards, favourite journeys

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

    how brain, become demons, process image

    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
    ٹرول
    0.46
    鯢
    0.46
     стиль
    0.45
    ཝ
    0.45
    墀
    0.45
     trimethyl
    0.44
    荭
    0.43
     მას
    0.43
    ार
    0.43
    ))=\
    0.43
    POSITIVE LOGITS
    s
    0.54
     generously
    0.47
    গ্রস্ত
    0.46
    stractions
    0.44
    </li>
    0.44
    StatusBadRequest
    0.44
    Sigma
    0.43
    鼓
    0.43
    慷
    0.42
    。</
    0.42
    Activations Density 0.000%

    No Known Activations