© 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. 107192
    Prev
    Next
    INDEX
    Explanations

    recurrence or repetition

    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
     again
    -2.39
     nuevamente
    -1.57
     wieder
    -1.42
     opět
    -1.34
     novamente
    -1.32
     Again
    -1.28
     also
    -1.20
     опять
    -1.16
     снова
    -1.11
     wiederum
    -1.09
    POSITIVE LOGITS
    r
    1.03
    "
    1.02
    st
    1.02
     japonesa
    1.01
     régle
    0.96
     чрез
    0.95
     elever
    0.95
    s
    0.93
     menging
    0.92
    近くの
    0.92
    Activations Density 0.012%

    No Known Activations