© 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. 17721
    Prev
    Next
    INDEX
    Explanations

    Conservative estimates, official links, news forecasts

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

    finding specific terms

    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
     dazz
    0.46
     librería
    0.45
     enfer
    0.44
     emoción
    0.43
     ආ
    0.42
     Jez
    0.42
     fabricación
    0.42
     asistencia
    0.41
     experiencia
    0.41
     experiência
    0.41
    POSITIVE LOGITS
     வகையான
    0.52
    ๓
    0.49
     важно
    0.48
    รายละเอียด
    0.45
     महत्वपूर्ण
    0.45
    byterian
    0.43
     ৪৫
    0.43
    онів
    0.42
    rekken
    0.42
    рін
    0.41
    Activations Density 0.000%

    No Known Activations