© 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. 27013
    Prev
    Next
    INDEX
    Explanations

    flirty, flustered, flag

    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
    b
    0.88
    al
    0.80
    field
    0.73
    n
    0.69
    rs
    0.67
    ้า
    0.65
    ล
    0.65
    d
    0.65
    led
    0.64
    a
    0.64
    POSITIVE LOGITS
     фла
    0.95
     フラ
    0.89
     flares
    0.85
    ’
    0.85
     flattering
    0.79
    Fl
    0.79
     فل
    0.78
     ফ্ল
    0.77
     flags
    0.77
     Flanagan
    0.75
    Activations Density 0.070%

    No Known Activations