© 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. 13139
    Prev
    Next
    INDEX
    Explanations

    key, crucial, paramount

    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
     incorporates
    0.48
    м
    0.46
     equips
    0.45
     adds
    0.44
    ренного
    0.42
    като
    0.42
    дям
    0.40
     dilengkapi
    0.39
    י
    0.39
     omnip
    0.39
    POSITIVE LOGITS
     बर्बाद
    0.43
    成功的
    0.43
    钊
    0.43
     성공
    0.43
     విజయ
    0.40
     ጥሩ
    0.40
     Erfolg
    0.38
    GetUser
    0.38
    туры
    0.38
     LH
    0.38
    Activations Density 0.151%

    No Known Activations