© 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-262K
    7. 139470
    Prev
    Next
    INDEX
    Explanations

    a followed by a noun

    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_262k_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
    FTR
    0.51
    urètre
    0.47
    Overse
    0.46
    𝟬
    0.46
    ތ
    0.46
     minuta
    0.44
     Гинд
    0.44
    ޓ
    0.44
     языка
    0.44
     ƙ
    0.43
    POSITIVE LOGITS
    ave
    0.49
     कोण
    0.45
    urnal
    0.40
    ,~
    0.40
     কোন
    0.40
     কে
    0.39
     siehe
    0.39
     flattened
    0.39
    ,
    0.39
    峰
    0.39
    Activations Density 0.001%

    No Known Activations