© 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. 11302
    Prev
    Next
    INDEX
    Explanations

    especially, initially, determined, like, fearing

    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
    媲
    0.52
     waardoor
    0.51
     '}';
    0.48
     preposition
    0.48
     wodurch
    0.47
    нную
    0.47
    𒁺
    0.46
    뭘
    0.46
    耱
    0.46
    𝚖
    0.46
    POSITIVE LOGITS
     selaku
    0.58
     having
    0.52
    ’
    0.50
     maupun
    0.47
    aware
    0.47
     had
    0.46
     despite
    0.46
     khususnya
    0.45
    作为一个
    0.45
     ,
    0.44
    Activations Density 0.068%

    No Known Activations