© 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. 64801
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and specific entities

    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
     éxitos
    -0.83
    ᚠ
    -0.81
    ⽅
    -0.80
     suffit
    -0.77
     campaigning
    -0.76
     Sortiment
    -0.76
    saus
    -0.75
    enovo
    -0.75
    endid
    -0.75
    advantages
    -0.75
    POSITIVE LOGITS
    Reynolds
    0.76
    家具
    0.74
    Nickname
    0.73
    UBA
    0.71
    dr
    0.71
    켜
    0.68
    styled
    0.68
    mono
    0.68
    taires
    0.68
     Coupled
    0.67
    Activations Density 0.028%

    No Known Activations