© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 40815
    Prev
    Next
    INDEX
    Explanations

    tokens not words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    2
    0.60
    ों
    0.53
    ים
    0.50
     indicar
    0.45
     voltam
    0.45
    ఫ
    0.44
    ات
    0.44
    ý
    0.44
     Tonawanda
    0.43
     Adrien
    0.43
    POSITIVE LOGITS
     змі
    0.45
     Pais
    0.44
     brib
    0.43
     최대
    0.43
    䇢
    0.42
     казіно
    0.42
     핵
    0.41
    शुल्क
    0.41
    Aile
    0.41
    лды
    0.40
    Activations Density 0.005%

    No Known Activations