© 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. 184358
    Prev
    Next
    INDEX
    Explanations

    future financial position

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

    No, json, renal failure

    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
    كة
    0.52
    شر
    0.49
    কে
    0.47
    كت
    0.47
    باً
    0.47
    Um
    0.44
     Wh
    0.44
    ბ
    0.44
    一个
    0.44
    কের
    0.44
    POSITIVE LOGITS
     alight
    0.59
    elective
    0.54
    elliptic
    0.54
     nuovo
    0.52
     වැඩි
    0.52
     ಅಲ್ಲಿ
    0.51
     peculiar
    0.51
     parochial
    0.51
     નવી
    0.51
     тощо
    0.50
    Activations Density 0.001%

    No Known Activations