© 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. 15036
    Prev
    Next
    INDEX
    Explanations

    vertex or velocity

    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
    一
    1.73
    t
    1.53
    d
    1.48
    ट
    1.46
    이
    1.43
    یم
    1.42
    ن
    1.42
    일
    1.41
    る
    1.40
    نا
    1.37
    POSITIVE LOGITS
    1.45
     devoured
    0.97
     deinen
    0.96
    to
    0.96
     heeft
    0.93
    €“
    0.92
    0.91
    其他
    0.89
     hath
    0.88
     hoher
    0.88
    Activations Density 0.022%

    No Known Activations