© 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. 77496
    Prev
    Next
    INDEX
    Explanations

    frequency counting words

    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
    autoplay
    -0.89
     warmest
    -0.84
     always
    -0.82
    初の
    -0.81
    berts
    -0.80
    늘
    -0.79
    日で
    -0.79
    一直
    -0.78
    ulex
    -0.78
     всегда
    -0.77
    POSITIVE LOGITS
     twice
    4.13
    twice
    3.20
     once
    3.02
     three
    2.80
     thrice
    2.67
    Twice
    2.55
     Twice
    2.45
     several
    2.31
    once
    2.30
     two
    2.28
    Activations Density 0.086%

    No Known Activations