© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 135791
    Prev
    Next
    INDEX
    Explanations

    ADHD and attention spans

    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
    ɤ
    0.45
    ilight
    0.39
     diode
    0.38
     SONG
    0.38
     केस
    0.37
     해석
    0.37
     философ
    0.37
    iriman
    0.37
    嘔
    0.37
     Song
    0.37
    POSITIVE LOGITS
    Attention
    1.43
     attention
    1.41
     Attention
    1.39
     ADHD
    1.30
     atención
    1.26
    attention
    1.26
    注意力
    1.16
     attenzione
    1.13
     atenção
    1.12
     Aufmerksamkeit
    1.08
    Activations Density 0.044%

    No Known Activations