© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 195135
    Prev
    Next
    INDEX
    Explanations

    big splurge

    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
    ക്കളുടെ
    0.41
    ুলের
    0.39
     partitioned
    0.35
    हो
    0.35
    ல்க
    0.35
     nicknamed
    0.35
     ፈ
    0.35
     ül
    0.35
     multiplies
    0.35
    利的
    0.35
    POSITIVE LOGITS
     segregation
    0.40
     тях
    0.39
    簡單
    0.39
    AMENTE
    0.39
    ajar
    0.36
    baixo
    0.36
    극장
    0.36
     всей
    0.35
    apur
    0.35
     Enjoy
    0.34
    Activations Density 0.002%

    No Known Activations