© 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. 86968
    Prev
    Next
    INDEX
    Explanations

    writing, loaded, country, customer, merchant

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

    bad hands

    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
     k
    0.51
     တော့
    0.47
     शह
    0.47
     Carthage
    0.46
     ဂ
    0.45
     Ars
    0.45
     Kxc
    0.44
     Hacienda
    0.44
     Ket
    0.44
     तृ
    0.44
    POSITIVE LOGITS
    口感
    0.46
    有一种
    0.41
    腎
    0.41
    "`
    0.40
    μένος
    0.40
    যখন
    0.39
    ้อน
    0.39
    ្នាំ
    0.39
    λογή
    0.38
    uiswing
    0.38
    Activations Density 0.002%

    No Known Activations