© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1191
    Prev
    Next
    INDEX
    Explanations

    gardening, DBA, budgeting, debugging

    np_acts-logits-general · gemini-2.5-flash-lite

    words related to gardening and horticulture.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ruju
    -2.47
    ﮦ
    -2.45
    erintah
    -2.41
    メリカ
    -2.41
    痦
    -2.36
    всегда
    -2.31
    s
    -2.30
    荩
    -2.23
    replyreport
    -2.22
    Ꮽ
    -2.20
    POSITIVE LOGITS
    the
    3.23
    these
    2.73
    and
    2.53
    cją
    2.52
    C
    2.47
     hablaba
    2.44
    they
    2.34
    ?”
    2.30
    %;
    2.28
    棡
    2.25
    Activations Density 0.003%

    No Known Activations