© 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. 8539
    Prev
    Next
    INDEX
    Explanations

    and then (

    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
     and
    -2.31
    麿
    -1.50
    \}=\
    -1.47
     которы
    -1.41
    broj
    -1.40
    mozilla
    -1.39
    ığımız
    -1.38
     cuyos
    -1.37
     conocidas
    -1.37
     called
    -1.36
    POSITIVE LOGITS
    ↵
    2.23
    </i>
    2.23
     caricatura
    1.76
    </b>
    1.66
     alltid
    1.55
     universitaria
    1.55
     castellano
    1.55
     creer
    1.53
     éta
    1.52
    就得
    1.51
    Activations Density 0.014%

    No Known Activations