© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7274
    Prev
    Next
    INDEX
    Explanations

    social networks and community

    np_acts-logits-general · gemini-2.5-flash-lite

    networking and community building

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     våra
    0.44
    原因是
    0.41
    人类
    0.39
    墘
    0.39
    ொழுது
    0.37
    可以说
    0.37
     nació
    0.36
    琙
    0.36
    䉍
    0.35
    嗥
    0.35
    POSITIVE LOGITS
    1
    0.46
    3
    0.45
     to
    0.43
     żeby
    0.40
    0
    0.39
    driven
    0.39
    6
    0.39
     aby
    0.38
     پرورش
    0.38
     influencers
    0.37
    Activations Density 0.091%

    No Known Activations