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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1473
    Prev
    Next
    INDEX
    Explanations

    bracketed numbers

    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
     empirical
    0.50
    $^{
    0.46
     pathogenesis
    0.45
     alleles
    0.44
     kingdoms
    0.43
    pH
    0.43
     accelerators
    0.42
     kinases
    0.42
     algebras
    0.41
     細胞
    0.41
    POSITIVE LOGITS
    тся
    0.40
    hbs
    0.40
     Politiker
    0.40
    ]}/
    0.39
     ////
    0.39
     Iris
    0.39
    ]
    0.39
    ")}}'
    0.38
    সরকারী
    0.38
    </s>
    0.38
    Activations Density 0.000%

    No Known Activations