© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3464
    Prev
    Next
    INDEX
    Explanations

    information transmission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    经纪
    0.63
    商家
    0.54
    职位
    0.54
    ujourd
    0.52
    षेक
    0.52
    欤
    0.52
     финанси
    0.51
    acariy
    0.51
    🏦
    0.51
     Prefeitura
    0.50
    POSITIVE LOGITS
     signal
    0.91
     OFDM
    0.90
     transmission
    0.84
     transmissions
    0.84
     transmit
    0.84
     waveform
    0.83
     narrowband
    0.83
    SNR
    0.82
     transmitted
    0.82
     waveforms
    0.80
    Activations Density 0.131%

    No Known Activations