© 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. 31-GEMMASCOPE-2-RES-262K
    7. 11566
    Prev
    Next
    INDEX
    Explanations

    Vibe Check

    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
    燾
    0.46
    _
    0.41
    得る
    0.37
    ■
    0.37
    㫣
    0.37
     biện
    0.35
    npmjs
    0.34
    ▩
    0.33
    ји
    0.33
     viewpoints
    0.33
    POSITIVE LOGITS
    0.40
     तथा
    0.39
     samt
    0.39
     bernama
    0.39
     oraz
    0.38
    wasser
    0.38
     Name
    0.37
     Seri
    0.37
     इस
    0.37
    그리고
    0.37
    Activations Density 0.039%

    No Known Activations