© 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. 16-GEMMASCOPE-2-RES-262K
    7. 137612
    Prev
    Next
    INDEX
    Explanations

    reporting speech or feeling

    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_16_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
    vorm
    0.65
    vand
    0.63
    $.)
    0.62
    vene
    0.61
    vaise
    0.59
     enligt
    0.59
    [++
    0.59
    vare
    0.58
    rit
    0.57
    venture
    0.57
    POSITIVE LOGITS
    0.95
    s
    0.78
    ی
    0.67
    نی
    0.67
     श्रमिकों
    0.64
    اری
    0.64
    ু
    0.63
    はお
    0.62
    민
    0.60
    ﺳ
    0.59
    Activations Density 0.005%

    No Known Activations