© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99023
    Prev
    Next
    INDEX
    Explanations

    MMP or chmod commands

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    </h3>
    -3.34
     geef
    -2.55
     encontre
    -2.41
    "}
    -2.34
    ية
    -2.30
     hunt
    -2.28
    ſſen
    -2.25
    ⸰
    -2.25
    “
    -2.23
     denkt
    -2.20
    POSITIVE LOGITS
    </b>
    2.63
     для
    2.36
    Tujuan
    2.20
    منبع
    2.20
    Kondisi
    2.14
    時間も
    2.13
     -
    2.13
    Kegiatan
    2.08
    Selanjutnya
    2.08
    Плюсы
    2.05
    Activations Density 0.007%

    No Known Activations