© 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. 37833
    Prev
    Next
    INDEX
    Explanations

    Consensus Panel

    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
    编辑
    -0.70
     Fryer
    -0.69
    妖
    -0.67
    ᅢ
    -0.66
    Gravity
    -0.66
     Must
    -0.65
     deben
    -0.64
     Queen
    -0.64
    see
    -0.61
    非
    -0.61
    POSITIVE LOGITS
    PROTOBUF
    0.71
    Barb
    0.69
    startY
    0.68
     bere
    0.68
    忡
    0.66
    утбу
    0.65
    SCOTT
    0.65
     Stardust
    0.65
    Ux
    0.64
    }}],
    0.64
    Activations Density 0.064%

    No Known Activations