© 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. 109112
    Prev
    Next
    INDEX
    Explanations

    initial value problems and boundary conditions

    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
    psz
    -0.76
    worten
    -0.75
    ogeneity
    -0.71
    𝖿
    -0.69
     algu
    -0.69
    abilia
    -0.69
     Tis
    -0.69
     こと
    -0.68
    ياء
    -0.66
    レポート
    -0.66
    POSITIVE LOGITS
     Initial
    2.20
     initial
    2.06
    Initial
    1.98
    initial
    1.96
     INITIAL
    1.66
     IPO
    1.63
     problem
    1.56
    INITIAL
    1.55
     Cauchy
    1.45
     problème
    1.42
    Activations Density 0.040%

    No Known Activations