© 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. 212456
    Prev
    Next
    INDEX
    Explanations

    people's actions and characteristics

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

    justifierBot

    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
    不太
    0.47
    。)
    0.44
    ittances
    0.42
    早
    0.42
     পুঁ
    0.41
    sometimes
    0.41
    .)
    0.40
     strung
    0.40
    perhaps
    0.39
    integrity
    0.39
    POSITIVE LOGITS
     человека
    0.52
     परिजनों
    0.48
    人々
    0.46
    ፣
    0.46
    人を
    0.45
     людини
    0.45
    ၊
    0.44
     म्हणाले
    0.44
     परिजन
    0.43
     mennesker
    0.43
    Activations Density 0.000%

    No Known Activations