© 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. 6625
    Prev
    Next
    INDEX
    Explanations

    RF signals and antennas

    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
     Dinosaur
    0.45
     kiş
    0.45
     नैतिक
    0.44
    <>();
    0.44
     अवि
    0.43
     ادائیگی
    0.42
    鄯
    0.42
    减肥
    0.41
     Dino
    0.41
    Token
    0.41
    POSITIVE LOGITS
     antenna
    1.76
     antennas
    1.69
     microwave
    1.60
     антен
    1.54
    antenna
    1.48
     Microwave
    1.47
     RF
    1.45
     Antenna
    1.45
     antena
    1.45
     antennes
    1.44
    Activations Density 0.050%

    No Known Activations