© 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. 31249
    Prev
    Next
    INDEX
    Explanations

    inherent qualities and properties

    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
    Advantage
    -0.78
    Depression
    -0.78
     Denim
    -0.78
    这样一个
    -0.77
    Anxiety
    -0.77
    更有
    -0.75
     Tension
    -0.74
     Août
    -0.74
     étoiles
    -0.73
     TON
    -0.73
    POSITIVE LOGITS
    ความ
    1.88
     inherent
    1.18
    sự
    1.11
    本当の
    1.11
     sự
    1.09
     độ
    1.06
    可爱
    1.02
     newfound
    1.02
     ความ
    1.01
     абсолю
    0.98
    Activations Density 0.242%

    No Known Activations