© 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. 127284
    Prev
    Next
    INDEX
    Explanations

    preposition or common phrase starter

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

    risk and existence of things

    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
    vori
    0.54
     கழி
    0.51
     那麼
    0.50
    cego
    0.50
     据
    0.49
    running
    0.48
     因為
    0.47
    lying
    0.47
    łam
    0.46
    SPI
    0.46
    POSITIVE LOGITS
     veritable
    0.47
     territoires
    0.47
    '
    0.46
    दरी
    0.46
    োদিত
    0.45
    ächer
    0.43
    ’
    0.43
     biologist
    0.43
     deciduous
    0.43
    rectionType
    0.43
    Activations Density 0.001%

    No Known Activations