© 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. 119669
    Prev
    Next
    INDEX
    Explanations

    then again

    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
    ت
    0.67
    ب
    0.65
    ون
    0.64
    는
    0.59
    은
    0.59
    т
    0.58
    ง
    0.58
    {
    0.57
    وی
    0.55
    )+(
    0.55
    POSITIVE LOGITS
     potrebbero
    0.57
     commandant
    0.53
    嬌
    0.52
    BOW
    0.51
     zásob
    0.51
     vrh
    0.50
    伌
    0.50
    範
    0.50
     víctimas
    0.49
     melhor
    0.49
    Activations Density 0.000%

    No Known Activations