© 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. 148352
    Prev
    Next
    INDEX
    Explanations

    Wiltshire and African locations

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

    uncovering hidden gems

    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
     infile
    0.52
    大利
    0.52
    acqua
    0.50
     imprison
    0.49
    álisis
    0.49
    ma
    0.47
    𝟮
    0.46
     फैली
    0.45
     বিদ
    0.45
     proclaims
    0.44
    POSITIVE LOGITS
    ਾ
    0.58
    れている
    0.49
    ոտ
    0.46
    앵
    0.46
    bewer
    0.45
     Tutak
    0.45
     cytokines
    0.45
    اہ
    0.44
    жет
    0.44
    餐饮
    0.44
    Activations Density 0.000%

    No Known Activations