© 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. 99855
    Prev
    Next
    INDEX
    Explanations

    job role title

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

    steps, lists, and formatting

    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
    Name
    0.48
    Data
    0.48
    Rs
    0.47
    РА
    0.46
    Key
    0.46
    Chennai
    0.46
    ouns
    0.45
    ↵
    0.45
    Nama
    0.45
    meister
    0.45
    POSITIVE LOGITS
     undulating
    0.49
     Nói
    0.49
     pudiera
    0.48
     sickening
    0.47
     cuisses
    0.46
     thickly
    0.45
     είναι
    0.45
     disminución
    0.44
     donning
    0.43
     sandals
    0.43
    Activations Density 0.002%

    No Known Activations