© 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. 92073
    Prev
    Next
    INDEX
    Explanations

    progresses slowly or gradually

    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
    Ų
    -0.89
    lindungan
    -0.88
    tude
    -0.74
     erneut
    -0.74
    ora
    -0.72
    era
    -0.72
     BNE
    -0.72
    øde
    -0.71
     even
    -0.70
    再次
    -0.69
    POSITIVE LOGITS
     slowly
    5.88
     gradual
    5.13
     gradually
    5.09
    slowly
    4.69
    Slowly
    4.59
     Slowly
    4.56
     постепенно
    3.92
     Gradually
    3.84
     slow
    3.55
    gradu
    3.42
    Activations Density 0.141%

    No Known Activations