© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 44931
    Prev
    Next
    INDEX
    Explanations

    hardware, software, AI, models

    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
     König
    0.46
     tarifa
    0.42
    棪
    0.40
     Izv
    0.40
     MHD
    0.38
     forage
    0.38
     hiszen
    0.37
     využ
    0.37
    簫
    0.36
     PAM
    0.36
    POSITIVE LOGITS
     punished
    0.52
    even
    0.50
     punishments
    0.49
    iiii
    0.46
    inu
    0.46
    till
    0.46
    themealdb
    0.46
    sexual
    0.45
    ̿
    0.45
    élo
    0.44
    Activations Density 0.033%

    No Known Activations