© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5854
    Prev
    Next
    INDEX
    Explanations

    Coachella Whitney Hetzel

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

    Disco Elysium

    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_53_width_65k_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
    ࿔
    0.48
     драматур
    0.48
    袠
    0.47
    ू
    0.47
    vadipine
    0.46
    ⿻
    0.46
    Ꮏ
    0.45
    AIRMAN
    0.45
    ⑴
    0.45
    ܂
    0.45
    POSITIVE LOGITS
     nis
    0.42
     cik
    0.40
     dug
    0.39
     sah
    0.39
     side
    0.38
     sı
    0.38
    sing
    0.38
     re
    0.37
    might
    0.37
     se
    0.37
    Activations Density 0.001%

    No Known Activations