© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63051
    Prev
    Next
    INDEX
    Explanations

    paste or provide

    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
     encontraba
    0.54
     precedent
    0.53
     homely
    0.50
     undeveloped
    0.49
    Sullivan
    0.48
    ﾝ
    0.48
    Ӏо
    0.47
     manoeuv
    0.47
    ＮＡＮＡ
    0.47
     cultivators
    0.46
    POSITIVE LOGITS
    凯
    0.43
     q
    0.42
    开启
    0.42
    代码
    0.41
     was
    0.41
    ма
    0.41
     oblig
    0.40
    ü
    0.40
    ூ
    0.40
    架构
    0.39
    Activations Density 0.008%

    No Known Activations