© 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. 49024
    Prev
    Next
    INDEX
    Explanations

    spin glass experiments

    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
    olah
    -0.72
    permissions
    -0.68
    мыш
    -0.66
    リスク
    -0.66
    Duck
    -0.66
     būt
    -0.66
    estim
    -0.65
     Duck
    -0.64
    POC
    -0.64
    faux
    -0.64
    POSITIVE LOGITS
    glass
    1.36
     glass
    1.35
     glassy
    1.21
    Glass
    1.16
     glasses
    1.06
     GLASS
    1.06
    GLASS
    1.03
    ガラス
    1.03
     Glass
    1.02
    玻璃
    0.99
    Activations Density 0.063%

    No Known Activations