© 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. 88296
    Prev
    Next
    INDEX
    Explanations

    specific names and objects

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

    military context, distinct values, major storm, busy streams

    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
     ม
    0.45
     約
    0.45
    dison
    0.43
    UCH
    0.43
    0.43
    ม
    0.43
    璘
    0.43
     us
    0.43
     chúng
    0.41
     Gaza
    0.40
    POSITIVE LOGITS
     carnival
    0.43
    蛉
    0.41
     carnaval
    0.41
    istik
    0.40
    तिर
    0.40
    テール
    0.40
    currentRow
    0.40
     характеризу
    0.39
     الحره
    0.39
     violinist
    0.39
    Activations Density 0.003%

    No Known Activations