© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 4105
    Prev
    Next
    INDEX
    Explanations

    signal reception and noise

    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_40_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
     skateboarding
    0.61
    skateboard
    0.54
     Sass
    0.51
     murderous
    0.51
     Skate
    0.51
     meringue
    0.49
    痱
    0.49
     Bowling
    0.49
    经纪
    0.49
    橐
    0.48
    POSITIVE LOGITS
     OFDM
    1.12
     IEEE
    1.05
     signal
    1.02
    IEEE
    1.01
    triangleq
    0.98
     demod
    0.97
     SNR
    0.95
    signal
    0.93
     transceiver
    0.93
    SNR
    0.92
    Activations Density 0.030%

    No Known Activations