© 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. 40-GEMMASCOPE-2-RES-262K
    7. 223162
    Prev
    Next
    INDEX
    Explanations

    communication manipulation techniques

    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_40_width_262k_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
     dator
    0.42
     closet
    0.40
     kred
    0.39
    ﻱ
    0.37
     lö
    0.37
     rozm
    0.37
     favourable
    0.36
     prie
    0.36
     pel
    0.36
     résoudre
    0.36
    POSITIVE LOGITS
    ດ
    0.43
    흑
    0.40
    फिर
    0.40
     DISPLAY
    0.40
     बुनियादी
    0.39
    海水
    0.38
    Puerto
    0.38
    军队
    0.38
    नीर
    0.38
    צים
    0.38
    Activations Density 0.001%

    No Known Activations