© 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. 64756
    Prev
    Next
    INDEX
    Explanations

    grade levels

    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
    epoch
    -0.86
     afirm
    -0.84
    ს
    -0.79
    چ
    -0.78
    cession
    -0.78
    atical
    -0.77
    MYSQL
    -0.76
     ۱۹
    -0.74
    Plex
    -0.74
    atores
    -0.74
    POSITIVE LOGITS
     fifth
    4.63
     sixth
    4.59
     fourth
    4.28
     seventh
    4.25
     eighth
    4.22
     ninth
    3.75
     third
    3.45
    fifth
    3.33
     elementary
    3.27
     kindergarten
    3.22
    Activations Density 0.118%

    No Known Activations