© 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. 31-GEMMASCOPE-2-RES-262K
    7. 52876
    Prev
    Next
    INDEX
    Explanations

    applications and treatment

    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_31_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
    '
    0.54
    ירה
    0.45
    ᄆ
    0.44
    ᅯ
    0.43
     rigor
    0.43
     week
    0.42
     पू
    0.42
     MENU
    0.42
     menu
    0.41
    ட்டம்
    0.41
    POSITIVE LOGITS
    ال
    0.45
    >\
    0.45
    loge
    0.44
    pane
    0.42
    closed
    0.42
    èn
    0.42
    quoi
    0.42
    limiting
    0.42
    ளிடம்
    0.41
    wa
    0.41
    Activations Density 0.000%

    No Known Activations