© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 131965
    Prev
    Next
    INDEX
    Explanations

    numbers and commas

    np_acts-logits-general · gemini-2.5-flash-lite

    protection, contact, answer, release, loneliness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ан
    0.50
    奇怪
    0.49
    IRIS
    0.46
    га
    0.45
    ı
    0.44
    Minister
    0.43
    thinkable
    0.43
    <unused696>
    0.43
    ഓ
    0.42
    ор
    0.42
    POSITIVE LOGITS
     لوب
    0.48
     postulates
    0.48
     rulers
    0.47
     forceps
    0.47
     artery
    0.47
     Gründung
    0.47
     ตำ
    0.47
     grows
    0.46
     Demp
    0.46
     becomes
    0.46
    Activations Density 0.003%

    No Known Activations