© 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. 79298
    Prev
    Next
    INDEX
    Explanations

    hating, hatred, haunting

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

    kinda followed by negative descriptions

    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
    Ї
    0.45
    한
    0.45
    締
    0.42
     машиналары
    0.41
    ফার
    0.40
    tees
    0.39
    IDs
    0.38
    Fest
    0.38
    বারের
    0.38
    Мы
    0.38
    POSITIVE LOGITS
     নৃশংস
    0.50
     hating
    0.48
     ฉาก
    0.46
     利
    0.46
     hatred
    0.46
     haunting
    0.44
     Byzant
    0.43
     वेबसाइट
    0.43
    olutely
    0.43
     childbirth
    0.43
    Activations Density 0.001%

    No Known Activations