© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12502
    Prev
    Next
    INDEX
    Explanations

    names ending in ard, oyne, eller, id, iff

    np_acts-logits-general · gemini-2.5-flash-lite

    people who are charismatic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     splendour
    0.47
     പ്രതിഷേധ
    0.47
    董事长
    0.46
     constate
    0.46
    企业家
    0.45
     periodistas
    0.45
     masterpieces
    0.45
    晿
    0.45
    ദ്ദേ
    0.44
     अध्यक्ष
    0.43
    POSITIVE LOGITS
    value
    0.49
     value
    0.47
     qualifies
    0.47
     currently
    0.46
    CO
    0.46
     hails
    0.46
    ity
    0.46
     ২৫
    0.45
     hydraulic
    0.45
     সৎ
    0.44
    Activations Density 0.329%

    No Known Activations