© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-65K
    4. 1401
    Prev
    Next
    INDEX
    Explanations

    edge and continuations

    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
    中です
    0.45
    jskich
    0.43
     untrue
    0.40
     سطح
    0.40
    hesize
    0.39
    ),]),
    0.38
     ennemis
    0.37
     bowel
    0.37
    েন
    0.37
    ")]),
    0.36
    POSITIVE LOGITS
     Edge
    0.90
     edge
    0.89
    Edge
    0.83
     edging
    0.78
     edges
    0.77
     EDGE
    0.77
    edge
    0.71
     edged
    0.71
    边缘
    0.67
     ed
    0.66
    Activations Density 0.042%

    No Known Activations