© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 116630
    Prev
    Next
    INDEX
    Explanations

    inversely proportional to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    мо
    1.00
    يقة
    0.90
    hető
    0.89
    ков
    0.89
    prüfung
    0.88
    ја
    0.87
     SoaException
    0.87
    ي
    0.87
    mehndi
    0.86
     escultura
    0.86
    POSITIVE LOGITS
     to
    1.21
     a
    1.09
     i
    0.81
     I
    0.80
     are
    0.79
     {\
    0.74
     mucus
    0.73
     o
    0.71
     determination
    0.71
     tarn
    0.71
    Activations Density 0.000%

    No Known Activations