© 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. 39242
    Prev
    Next
    INDEX
    Explanations

    solidification, positivities, hemosider, montage

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

    words starting with "posi" or "soli" such as "positive," "position," or "solidification."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    〜。
    -2.20
    ～。
    -2.20
    。】
    -2.19
     绒
    -2.17
    于是
    -2.09
     eneste
    -2.09
    (^^)
    -2.06
    錀
    -2.06
     dupa
    -2.05
    یکن
    -2.02
    POSITIVE LOGITS
    轳
    2.86
    a
    2.80
    ”
    2.63
    e
    2.52
    ar
    2.48
    の上に
    2.45
     stalwart
    2.45
    actéristi
    2.44
     "
    2.38
    喾
    2.36
    Activations Density 0.009%

    No Known Activations