© 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. 93640
    Prev
    Next
    INDEX
    Explanations

    posting online content

    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
    다
    0.97
    2
    0.80
    ير
    0.77
    the
    0.77
    hg
    0.75
    ان
    0.71
    ين
    0.66
    ה
    0.66
    aw
    0.64
    falling
    0.64
    POSITIVE LOGITS
     posta
    0.77
     postings
    0.73
     are
    0.72
     tentang
    0.71
     posting
    0.69
     onto
    0.69
     hostess
    0.68
    การ
    0.68
     postes
    0.67
     for
    0.66
    Activations Density 0.045%

    No Known Activations