© 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. 42418
    Prev
    Next
    INDEX
    Explanations

    at followed by a city name

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

    studying art

    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
     কাজে
    0.52
    ukkh
    0.52
    Ι
    0.50
     namani
    0.49
     रिश्
    0.47
     правильно
    0.47
     HTMLSc
    0.47
     синте
    0.47
    irteen
    0.46
    cevam
    0.46
    POSITIVE LOGITS
    拖
    0.49
    茅
    0.47
     playground
    0.46
    幼児
    0.46
    意外
    0.45
    煞
    0.45
     toilette
    0.44
    胎
    0.43
     Gant
    0.43
    盛
    0.43
    Activations Density 0.000%

    No Known Activations