© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99465
    Prev
    Next
    INDEX
    Explanations

    usernames or identifiers

    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_34/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
     kriminal
    -1.17
     indien
    -1.09
     galeri
    -1.05
     kompeti
    -1.02
     teori
    -1.00
     sábado
    -1.00
     vokal
    -0.99
     harap
    -0.98
     teka
    -0.98
     klasik
    -0.97
    POSITIVE LOGITS
     afectadas
    1.26
     trastornos
    1.23
    孰
    1.21
     nobody
    1.17
     habituales
    1.14
     apropiado
    1.14
     Mr
    1.12
     atractivos
    1.12
    apimachinery
    1.10
     profundas
    1.10
    Activations Density 0.042%

    No Known Activations