© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 55575
    Prev
    Next
    INDEX
    Explanations

    observing, describing, states, actions

    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
    father
    0.49
     magari
    0.45
     Comune
    0.44
     তহবিল
    0.44
    familyName
    0.43
    ﻱ
    0.43
    གས་
    0.43
     kanske
    0.42
     নাহি
    0.40
     ensue
    0.40
    POSITIVE LOGITS
     हर्षवर्धन
    0.48
     ø
    0.46
     เริ่ม
    0.46
     ওয়ে
    0.46
     αν
    0.44
    opolitical
    0.44
    न्यूयॉर्क
    0.43
     वेब
    0.43
     ट्वीट
    0.43
     ምክንያ
    0.43
    Activations Density 0.023%

    No Known Activations