© 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. 105492
    Prev
    Next
    INDEX
    Explanations

    suicide attempts

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

    feeling complicated experience

    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
    ian
    0.55
    iet
    0.50
     movie
    0.48
     تر
    0.46
    owanie
    0.46
     election
    0.46
    hara
    0.45
     ܀
    0.44
    öre
    0.44
     holidays
    0.44
    POSITIVE LOGITS
     аксе
    0.50
     kucch
    0.48
     базы
    0.47
     squarely
    0.46
    центри
    0.45
    ъек
    0.44
     базо
    0.44
     кеңселер
    0.44
     unsurprisingly
    0.44
     кабинет
    0.43
    Activations Density 0.001%

    No Known Activations