© 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. 66162
    Prev
    Next
    INDEX
    Explanations

    in scientific contexts

    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
     täglichen
    -1.70
    —“
    -1.58
     Détails
    -1.52
    ANIEL
    -1.51
     bloquer
    -1.49
     TAMBÉM
    -1.48
     Darauf
    -1.45
    一个
    -1.42
     dibuka
    -1.42
    𝟎
    -1.41
    POSITIVE LOGITS
    și
    1.37
    bingen
    1.28
    </em>
    1.26
     ktoré
    1.26
    UCIÓN
    1.23
     them
    1.22
     in
    1.19
    embal
    1.19
     nu
    1.18
     ul
    1.18
    Activations Density 0.024%

    No Known Activations