© 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. 31-GEMMASCOPE-2-RES-262K
    7. 37967
    Prev
    Next
    INDEX
    Explanations

    value preceded by 'is'

    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_31_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
     所以
    0.43
     যেহেতু
    0.42
     since
    0.41
    3
    0.40
    existe
    0.40
     emphatic
    0.39
     दिखी
    0.39
    :
    0.39
     allora
    0.38
    idP
    0.38
    POSITIVE LOGITS
    .[/
    0.64
     copyspace
    0.52
    .​​
    0.50
    .。
    0.46
    .\\
    0.44
    .`
    0.44
    .</
    0.42
    。</
    0.42
    ¹.
    0.42
    ﹝
    0.41
    Activations Density 0.047%

    No Known Activations