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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 14383
    Prev
    Next
    INDEX
    Explanations

    code and chorus segments

    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
     kr
    0.44
     ganz
    0.44
     preterm
    0.41
     W
    0.39
    艐
    0.39
     P
    0.37
     premat
    0.34
     i
    0.34
     •
    0.34
     Whe
    0.34
    POSITIVE LOGITS
    Logout
    0.40
    Payout
    0.39
     главного
    0.39
    angulo
    0.38
    btnLogout
    0.38
    ත්වය
    0.37
    barui
    0.37
    ጼ
    0.37
    apal
    0.37
    isHidden
    0.37
    Activations Density 0.105%

    No Known Activations