© 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-262K
    4. 134468
    Prev
    Next
    INDEX
    Explanations

    Font Awesome icons thin style

    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
    ])[
    0.42
    )^{*}\
    0.41
     неда
    0.39
    ﹰ
    0.38
    òn
    0.37
    ჲ
    0.37
    зал
    0.36
    ێر
    0.36
    tolyl
    0.35
    于
    0.35
    POSITIVE LOGITS
     Flip
    0.43
     comunic
    0.39
     beacon
    0.39
     linkedin
    0.39
     Governance
    0.39
     saute
    0.39
     lum
    0.38
     compone
    0.38
     essenti
    0.38
     flip
    0.37
    Activations Density 0.000%

    No Known Activations