© 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. 40-GEMMASCOPE-2-RES-262K
    7. 6090
    Prev
    Next
    INDEX
    Explanations

    canvas context

    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_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
    ﻯ
    0.43
     শোভ
    0.42
    Probit
    0.41
    TreeWidgetItem
    0.39
     sulfonic
    0.39
    銠
    0.39
    蕤
    0.39
    >\<^
    0.38
     なさい
    0.38
     आइकॉन
    0.38
    POSITIVE LOGITS
     canvas
    2.25
     Canvas
    2.08
    Canvas
    1.98
    canvas
    1.94
     canvases
    1.78
     CANVAS
    1.70
     canv
    1.54
    画布
    1.48
     lienzo
    1.34
    캔
    1.15
    Activations Density 0.036%

    No Known Activations