© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 120519
    Prev
    Next
    INDEX
    Explanations

    certificates and services

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

    appointed Altman, debated whether

    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_31_width_262k_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
    偶尔
    0.53
    ,}$
    0.50
     crimen
    0.49
    輙
    0.48
    Ι
    0.47
     occasionally
    0.47
    ILAR
    0.47
    ,]$
    0.46
     itself
    0.46
     иногда
    0.46
    POSITIVE LOGITS
     子
    0.47
    state
    0.46
    ቷ
    0.46
    st
    0.44
    grilled
    0.44
     CNN
    0.44
    avaient
    0.42
    漏
    0.41
     stora
    0.41
    Galer
    0.41
    Activations Density 0.001%

    No Known Activations