© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 36211
    Prev
    Next
    INDEX
    Explanations

    direct assignment

    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_31_width_65k_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
     anhydride
    0.45
    ureen
    0.44
     水
    0.44
     sunken
    0.44
    ০০
    0.43
     went
    0.42
     payee
    0.42
    蛋白
    0.41
     常
    0.41
     distiller
    0.40
    POSITIVE LOGITS
     désormais
    0.52
     Plusieurs
    0.48
     Quais
    0.46
    เพิ่มเติม
    0.44
     égal
    0.44
     combinação
    0.44
     dispositivi
    0.43
     modèles
    0.43
     Muchos
    0.43
     combinación
    0.42
    Activations Density 0.035%

    No Known Activations