© 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. 78023
    Prev
    Next
    INDEX
    Explanations

    recursive or recurrent followed by specific terms

    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
    又是一
    -0.82
     inizio
    -0.81
    カロリー
    -0.80
    wordpress
    -0.79
    ciated
    -0.78
    𝗕
    -0.78
     rotate
    -0.78
     Auswirkungen
    -0.77
    価値
    -0.76
     forças
    -0.75
    POSITIVE LOGITS
    RELATION
    0.85
     relations
    0.85
     mismos
    0.82
    ที่ดี
    0.81
    生素
    0.81
     partitioning
    0.81
     satın
    0.80
    гмент
    0.80
    ity
    0.79
     afspraak
    0.79
    Activations Density 0.049%

    No Known Activations