© 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. 116452
    Prev
    Next
    INDEX
    Explanations

    strength and other qualities

    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
    实力
    -1.02
    強度
    -0.90
     Powell
    -0.88
     strengths
    -0.88
     powerhouse
    -0.84
    Dz
    -0.84
    パワ
    -0.83
     Strengths
    -0.81
    Powell
    -0.80
     plumas
    -0.79
    POSITIVE LOGITS
     endurance
    0.97
     able
    0.83
    Dimanche
    0.73
    Endurance
    0.73
     invasion
    0.72
     晒
    0.72
     duration
    0.71
    วย
    0.71
    ขนาด
    0.71
    ={`${
    0.70
    Activations Density 0.066%

    No Known Activations