© 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. 11312
    Prev
    Next
    INDEX
    Explanations

    successful brands and proprietors

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

    self-preservation, minimizing losses

    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
    en
    0.57
    ie
    0.56
    ere
    0.55
    yla
    0.54
     l
    0.53
    il
    0.52
    ia
    0.52
    vi
    0.51
    ari
    0.50
    iri
    0.50
    POSITIVE LOGITS
     ресторан
    0.66
    лизи
    0.60
    蛋白質
    0.60
    污水
    0.58
    酒店
    0.57
    收费
    0.57
    餐厅
    0.55
    логу
    0.54
    𝘢
    0.54
    ร้าน
    0.54
    Activations Density 0.000%

    No Known Activations