© 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. 6166
    Prev
    Next
    INDEX
    Explanations

    meaningful word pairings

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

    modelmodel trained, IT teams, next element

    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
     საქართველოს
    0.41
     সেই
    0.40
    ⁄
    0.40
    .}\
    0.40
    ————
    0.39
    —
    0.39
     Skywalker
    0.38
     اسماع
    0.38
     AppleWebKit
    0.37
     Syair
    0.37
    POSITIVE LOGITS
    ˛
    0.37
     했습니다
    0.37
    ल्ली
    0.36
    日上午
    0.35
    老大
    0.35
    ピアス
    0.35
    یکس
    0.34
    ńskie
    0.34
    চরণ
    0.34
    ыл
    0.33
    Activations Density 0.208%

    No Known Activations