© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 45650
    Prev
    Next
    INDEX
    Explanations

    Google DeepMind

    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
     L
    0.47
     regularization
    0.44
     indebtedness
    0.42
     your
    0.42
     P
    0.41
     any
    0.40
     the
    0.40
     you
    0.40
     finan
    0.39
     financier
    0.38
    POSITIVE LOGITS
    ៦
    0.42
    INGS
    0.40
    írus
    0.40
    AR
    0.39
    ný
    0.38
     হবে
    0.38
     serão
    0.38
    YLE
    0.38
    Scope
    0.38
    ής
    0.37
    Activations Density 0.038%

    No Known Activations