© 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. 41135
    Prev
    Next
    INDEX
    Explanations

    resume example, stories behind

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

    Roblox Studio

    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
    ﾞ
    0.56
     in
    0.52
     結婚
    0.50
     iter
    0.49
     int
    0.48
     numero
    0.48
    ¨
    0.47
     spandex
    0.46
     二
    0.46
     inaugur
    0.46
    POSITIVE LOGITS
     Fälle
    0.45
     Cé
    0.44
    𝒜
    0.43
    Roof
    0.43
     Fence
    0.41
    ंता
    0.41
    毁
    0.41
    🛖
    0.41
    тера
    0.41
    Lynn
    0.41
    Activations Density 0.000%

    No Known Activations