© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65738
    Prev
    Next
    INDEX
    Explanations

    supplies, support, energy, features, solutions

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

    access to real-time information

    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
     dilengkapi
    0.41
     খু
    0.39
    刄
    0.37
     reconnaître
    0.37
    线上
    0.37
     instar
    0.37
     periodista
    0.36
     empate
    0.36
     bahagia
    0.36
    னர்
    0.36
    POSITIVE LOGITS
    including
    0.59
    fuels
    0.51
    Including
    0.48
    eud
    0.45
    fum
    0.45
    f
    0.44
    element
    0.43
    idet
    0.43
    ices
    0.43
    zd
    0.43
    Activations Density 0.215%

    No Known Activations