© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73829
    Prev
    Next
    INDEX
    Explanations

    collection and comparable types

    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
    </i>
    -1.73
    a
    -1.65
    ↵↵
    -1.64
     and
    -1.59
    c
    -1.55
    f
    -1.50
    ar
    -1.45
    od
    -1.43
    si
    -1.41
    an
    -1.40
    POSITIVE LOGITS
    橚
    1.54
     eviden
    1.38
    已经有
    1.37
     esso
    1.36
    jetos
    1.34
     Новости
    1.34
    pieza
    1.33
     dovr
    1.32
     dirit
    1.32
     metropolitana
    1.31
    Activations Density 0.021%

    No Known Activations