© 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. 175091
    Prev
    Next
    INDEX
    Explanations

    look forward to

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

    filtering options

    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
    㝢
    0.54
    জীবনে
    0.48
     последствия
    0.44
     избе
    0.44
    躹
    0.43
    த்தைக்
    0.43
     fieldContext
    0.43
     மக்களுக்கு
    0.42
    DataDiv
    0.42
     존재
    0.42
    POSITIVE LOGITS
     tariff
    0.43
     narcotics
    0.42
     Galleria
    0.42
     master
    0.41
    jPanel
    0.41
     trade
    0.40
     CNG
    0.40
     Cartier
    0.40
     cartel
    0.39
    ’
    0.39
    Activations Density 0.001%

    No Known Activations