© 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. 31-GEMMASCOPE-2-RES-65K
    7. 20795
    Prev
    Next
    INDEX
    Explanations

    radio signals and interference

    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_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
    🍧
    0.57
    🍮
    0.57
     yemek
    0.53
    猙
    0.52
    食物
    0.50
    ukiy
    0.50
    🍨
    0.50
     mewah
    0.49
    谄
    0.48
     shameful
    0.47
    POSITIVE LOGITS
     radio
    1.45
     Radio
    1.29
     VHF
    1.23
    Radio
    1.23
    radio
    1.21
     antenna
    1.19
     antennas
    1.19
     радио
    1.19
     radios
    1.17
     रेडियो
    1.17
    Activations Density 0.138%

    No Known Activations