© 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. 41-GEMMASCOPE-2-RES-262K
    7. 102906
    Prev
    Next
    INDEX
    Explanations

    RF amplifiers

    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_all/layer_41_width_262k_l0_big
    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
     Latham
    0.39
     अल्प
    0.37
    颂
    0.37
     аў
    0.37
    ائِ
    0.37
     trope
    0.36
     slowing
    0.36
     bounce
    0.35
    ishments
    0.35
    挀
    0.35
    POSITIVE LOGITS
     PA
    0.60
     amplifier
    0.59
     Amplifier
    0.59
    PA
    0.54
    RF
    0.52
     amplifiers
    0.52
     RF
    0.51
    amplifier
    0.51
     amph
    0.49
     amplification
    0.48
    Activations Density 0.001%

    No Known Activations