© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 120453
    Prev
    Next
    INDEX
    Explanations

    launch

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

    negative effects and actions

    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
    郆
    0.62
    Exe
    0.52
    Disco
    0.50
    mak
    0.47
    ارت
    0.47
     universitet
    0.47
    ırmak
    0.46
     privata
    0.46
    ğine
    0.46
    眅
    0.46
    POSITIVE LOGITS
     urine
    0.49
     wastewater
    0.49
     pesticide
    0.46
     slew
    0.45
     lavage
    0.45
     spray
    0.44
     ceramic
    0.44
     competing
    0.43
     urinary
    0.43
     degenerate
    0.43
    Activations Density 0.001%

    No Known Activations