© 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. 16-GEMMASCOPE-2-RES-262K
    7. 143617
    Prev
    Next
    INDEX
    Explanations

    Amogus, skinning, woke, Bourguiba

    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
    text
    0.61
    Text
    0.60
    types
    0.55
    source
    0.54
    ｻ
    0.52
    is
    0.51
    Property
    0.50
    Forward
    0.50
    tene
    0.50
    त्रेयी
    0.49
    POSITIVE LOGITS
    ه
    0.71
     leapt
    0.57
    ה
    0.57
     profondeur
    0.56
     tiros
    0.55
     leaned
    0.54
    레이
    0.53
     প্রভৃতি
    0.53
    い
    0.53
     molybdenum
    0.53
    Activations Density 0.000%

    No Known Activations