© 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. 34-GEMMASCOPE-RES-131K
    7. 57560
    Prev
    Next
    INDEX
    Explanations

    information and details

    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
    however
    -0.84
    Biochemical
    -0.84
     sowohl
    -0.82
    WithValue
    -0.80
     American
    -0.79
    crania
    -0.79
     angustia
    -0.79
     Auswahl
    -0.78
    ใด
    -0.78
     wysok
    -0.77
    POSITIVE LOGITS
     informações
    1.26
     information
    1.26
     informazioni
    1.15
    信息
    1.05
     detaljer
    1.04
     informations
    1.04
     details
    0.95
    Información
    0.95
     ottenuto
    0.93
    лец
    0.93
    Activations Density 0.078%

    No Known Activations