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

    Neuronpedia

    Jacobian LensNEW
    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. 10738
    Prev
    Next
    INDEX
    Explanations

    writing requests

    np_acts-logits-general · gemini-2.5-flash-lite

    instructions or directive language (imperative requests addressed to the model).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    ሳሪያ
    0.34
    renderCamera
    0.34
    становка
    0.33
    SplitContainer
    0.32
     النو
    0.32
    轎
    0.31
     StandardScaler
    0.31
     кеңселер
    0.31
     ঔষধ
    0.30
    桕
    0.30
    POSITIVE LOGITS
    ゙
    0.43
    selves
    0.41
    ん
    0.40
    he
    0.40
    therners
    0.40
    ｇ
    0.40
    wolves
    0.39
    cs
    0.39
     ayah
    0.38
    ri
    0.38
    Activations Density 0.037%

    No Known Activations