© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 130
    Prev
    Next
    INDEX
    Explanations

    explaining the way

    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_40_width_65k_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
    ↵
    0.29
     which
    0.27
    There
    0.26
    </u>
    0.25
     appears
    0.24
    isely
    0.24
     a
    0.24
    <unused2130>
    0.24
    ("
    0.24
    The
    0.23
    POSITIVE LOGITS
     Tatsache
    0.58
     fact
    0.54
     faptul
    0.45
     inability
    0.44
     immense
    0.44
     absurdity
    0.43
     sheer
    0.43
     insistence
    0.42
     lack
    0.41
     enorm
    0.41
    Activations Density 0.597%

    No Known Activations