© 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. 218595
    Prev
    Next
    INDEX
    Explanations

    foreign project investigation

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

    PROJECT

    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
    வைக்
    0.47
    alve
    0.47
    <0xA9>
    0.47
     saute
    0.46
     sé
    0.45
     mandated
    0.45
     celestial
    0.45
     sacram
    0.45
     barbit
    0.44
    鵲
    0.44
    POSITIVE LOGITS
     프로젝트
    0.51
     investigación
    0.51
     проекта
    0.50
     এলাকায়
    0.48
     PROJECT
    0.47
     বদলে
    0.47
     ITEM
    0.47
     проекты
    0.46
     investigadores
    0.45
     araştırm
    0.44
    Activations Density 0.001%

    No Known Activations