© 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. 196590
    Prev
    Next
    INDEX
    Explanations

    strengthens, verification, tendency, few

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

    bring insect repellent

    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
    реги
    0.55
    webs
    0.51
    র
    0.48
    event
    0.47
    寄存
    0.47
    chodu
    0.47
    le
    0.47
    糖
    0.47
    iore
    0.46
    ees
    0.46
    POSITIVE LOGITS
     gray
    0.54
     GRAY
    0.46
     MU
    0.46
     среди
    0.44
    ༨
    0.44
     grey
    0.44
     Gray
    0.42
    atinib
    0.42
     outings
    0.41
     сучас
    0.41
    Activations Density 0.001%

    No Known Activations