© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 88548
    Prev
    Next
    INDEX
    Explanations

    habit-forming products; Spanish Monday; known as; wrapped canvas

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

    listing structure or enumeration

    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
     kết
    0.47
     ت
    0.41
     الح
    0.41
    Hold
    0.41
     voter
    0.41
    subtract
    0.41
     swearing
    0.40
     bears
    0.40
     incest
    0.40
     пря
    0.40
    POSITIVE LOGITS
     당시
    0.52
    etzte
    0.46
    的那
    0.46
    OUND
    0.45
    ERAL
    0.44
    블
    0.44
    όμε
    0.43
    emento
    0.43
     Fahrzeuge
    0.43
    affe
    0.42
    Activations Density 0.002%

    No Known Activations