© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3489
    Prev
    Next
    INDEX
    Explanations

    high quality products

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

    improving quality

    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_53_width_65k_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
    훤
    0.37
    toni
    0.36
    toh
    0.36
    倖
    0.35
    Ꮒ
    0.34
    僳
    0.34
    ColorScheme
    0.33
     ఊ
    0.33
     అధ్యక్ష
    0.33
    izoph
    0.32
    POSITIVE LOGITS
     quality
    5.03
    quality
    4.78
     Quality
    4.69
    Quality
    4.66
     QUALITY
    4.59
     qualidade
    4.50
     Qualität
    4.47
     calidad
    4.41
     qualité
    4.41
     qualità
    4.38
    Activations Density 0.401%

    No Known Activations