© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3592
    Prev
    Next
    INDEX
    Explanations

    South Africa

    np_acts-logits-general · gemini-2.5-flash-lite

    creative generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ...."
    0.37
    复
    0.37
     sche
    0.37
    ----+
    0.37
    ']*
    0.36
     indeed
    0.36
     Band
    0.36
     biomedical
    0.36
     Henry
    0.36
     అల
    0.36
    POSITIVE LOGITS
     ​​
    0.63
    ̵
    0.62
     “,
    0.55
    Ე
    0.55
    Რ
    0.54
    Ბ
    0.52
    Ა
    0.52
     XNUMX
    0.52
    Მ
    0.49
    Ს
    0.48
    Activations Density 0.017%

    No Known Activations