© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76204
    Prev
    Next
    INDEX
    Explanations

    looping by length

    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
     genügend
    -0.94
     wenigstens
    -0.90
     ausreichend
    -0.88
    épar
    -0.88
     Gesells
    -0.87
     všetko
    -0.85
     ottima
    -0.85
     sirven
    -0.84
     unangemess
    -0.84
    érance
    -0.84
    POSITIVE LOGITS
     len
    1.66
     length
    1.52
    len
    1.29
    length
    1.25
     Length
    1.16
    Length
    1.13
    Len
    1.05
     Len
    1.04
     дли
    1.03
     LENGTH
    1.02
    Activations Density 0.007%

    No Known Activations