© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2700
    Prev
    Next
    INDEX
    Explanations

    tour operator discounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aniyati
    1.01
     privati
    0.94
     инфра
    0.89
     sentire
    0.87
    esas
    0.85
     requestCode
    0.85
    埴
    0.85
     onRequest
    0.84
    ICs
    0.84
    ната
    0.83
    POSITIVE LOGITS
    v
    1.67
     Brothers
    1.54
    ↵↵
    1.35
     Brother
    1.32
     v
    1.31
     Enlarg
    1.30
     Pry
    1.30
     Filtration
    1.29
     Fr
    1.27
    rh
    1.26
    Activations Density 0.101%

    No Known Activations