© 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. 43064
    Prev
    Next
    INDEX
    Explanations

    stage. begins. of yoga. the alarm. the USA. the U

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

    release of hostages held in Gaza for Palestinians

    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
    ነው
    0.45
    speedboat
    0.44
     компанией
    0.43
    Wildlife
    0.42
    leyeceğiz
    0.42
    嘞
    0.42
    野生
    0.41
    ük
    0.41
    espèces
    0.41
    ုန်
    0.41
    POSITIVE LOGITS
     usual
    0.48
     فون
    0.46
     direction
    0.44
    的方向
    0.44
     antif
    0.43
    افظ
    0.43
     பொதுவாக
    0.41
     পাশ্চাত্য
    0.41
     misc
    0.41
     wand
    0.41
    Activations Density 0.000%

    No Known Activations