© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82699
    Prev
    Next
    INDEX
    Explanations

    provided materials

    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
    сма
    -0.71
    Permission
    -0.69
    讯
    -0.68
     Ofic
    -0.68
    贝尔
    -0.68
    USER
    -0.67
    strncmp
    -0.67
     Alum
    -0.66
     actions
    -0.65
     adel
    -0.65
    POSITIVE LOGITS
     Russia
    0.71
     wmns
    0.66
    Enabling
    0.65
     卫
    0.65
    plex
    0.65
    ામ
    0.65
    становка
    0.64
    卫
    0.64
    CIN
    0.64
     Voigt
    0.64
    Activations Density 0.087%

    No Known Activations