© 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. 30622
    Prev
    Next
    INDEX
    Explanations

    code/technical instruction

    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
    0.40
    8
    0.40
     O
    0.39
    추
    0.39
    onym
    0.39
     P
    0.38
     Sta
    0.38
     Positive
    0.38
     Videos
    0.37
    OP
    0.37
    POSITIVE LOGITS
     loosening
    0.50
     প্রজাতির
    0.46
    expansive
    0.46
     راہ
    0.44
     транспорти
    0.44
     exasper
    0.44
     образова
    0.43
     "</
    0.43
    recognizable
    0.43
     donne
    0.42
    Activations Density 0.001%

    No Known Activations