© 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. 44996
    Prev
    Next
    INDEX
    Explanations

    persistent issues

    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
    f
    0.46
     plummeted
    0.46
     migrated
    0.46
    data
    0.46
     salsa
    0.45
     rehearsals
    0.44
     detectable
    0.44
     blockbuster
    0.44
    migrate
    0.43
     hailed
    0.42
    POSITIVE LOGITS
    䍘
    0.57
     فإن
    0.48
    㓈
    0.48
    美术
    0.46
     무엇
    0.46
     Collage
    0.46
    溇
    0.45
    ഠ
    0.45
    ഞ
    0.45
     यदि
    0.44
    Activations Density 0.001%

    No Known Activations