© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105971
    Prev
    Next
    INDEX
    Explanations

    ml or min

    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
     then
    -2.02
    !
    -1.52
     here
    -1.46
    </h3>
    -1.35
    if
    -1.33
     in
    -1.26
    后再
    -1.26
    osoba
    -1.25
     each
    -1.23
    ].
    -1.23
    POSITIVE LOGITS
     letzt
    1.31
    MigrationBuilder
    1.29
    utenants
    1.28
    ageable
    1.27
    pography
    1.23
    ppled
    1.20
    Initially
    1.20
    pples
    1.19
    CONCLUS
    1.19
    naments
    1.18
    Activations Density 0.144%

    No Known Activations