© 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. 49475
    Prev
    Next
    INDEX
    Explanations

    coding and classification

    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
    こな
    -0.80
     skrevet
    -0.79
    рот
    -0.77
    village
    -0.77
    wesenheit
    -0.75
    щики
    -0.70
    Gif
    -0.70
    🐜
    -0.70
    René
    -0.69
    Parameterized
    -0.68
    POSITIVE LOGITS
     coder
    1.16
     CDI
    1.10
     Encoder
    1.05
    coder
    1.01
    coders
    0.97
     Coding
    0.96
     encoder
    0.96
    Coding
    0.94
    coding
    0.93
     coding
    0.92
    Activations Density 0.015%

    No Known Activations