© 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. 41478
    Prev
    Next
    INDEX
    Explanations

    principal, virtual machine

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

    explaining concepts or guidance

    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
     промышленности
    0.47
    ራ
    0.43
    ০০০
    0.42
     Standing
    0.39
     denominado
    0.39
     chinh
    0.38
    κή
    0.38
     σύμφωνα
    0.38
     напрямую
    0.38
    的价格
    0.38
    POSITIVE LOGITS
    src
    0.46
    ㄈ
    0.45
     aDict
    0.45
    id
    0.45
    का
    0.44
    sq
    0.44
    df
    0.44
    newInstance
    0.44
     outlier
    0.42
    dirs
    0.42
    Activations Density 0.000%

    No Known Activations