© 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. 109379
    Prev
    Next
    INDEX
    Explanations

    professional anthology, orchestra, runway show

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

    desire or preference

    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
    ن
    0.52
    كرة
    0.52
     করুন
    0.52
    ună
    0.50
    níci
    0.50
    يفي
    0.50
    ًا
    0.49
    ాడు
    0.49
    槍
    0.48
    把你
    0.48
    POSITIVE LOGITS
     bilateral
    0.45
     yield
    0.45
     being
    0.45
     이야기를
    0.43
    datas
    0.42
     puddle
    0.42
     spectrometer
    0.42
    .’
    0.41
     benzene
    0.41
    ri
    0.41
    Activations Density 0.000%

    No Known Activations