© 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-262K
    7. 7401
    Prev
    Next
    INDEX
    Explanations

    emphasis on positive qualities

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

    genuine and profound qualities

    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_262k_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
    ټ
    0.60
    ᆭ
    0.55
    larda
    0.53
    ।]
    0.52
    ேட்
    0.52
    ফো
    0.52
    t
    0.52
     `:`
    0.51
    ol
    0.51
    உங்கள்
    0.50
    POSITIVE LOGITS
    真正的
    0.82
     truly
    0.77
     verdadeira
    0.66
     সত্যিকারের
    0.62
     true
    0.62
    真正
    0.61
     Truly
    0.61
     véritable
    0.57
     verdadero
    0.56
     verdadera
    0.55
    Activations Density 0.028%

    No Known Activations