© 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. 175356
    Prev
    Next
    INDEX
    Explanations

    android apps to your computer

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

    explanations of meaning or purpose

    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
    í
    0.66
    im
    0.57
     проект
    0.49
    ín
    0.48
    endereco
    0.48
     प्रकल्
    0.47
    ud
    0.47
    tools
    0.45
     руководи
    0.44
    invention
    0.44
    POSITIVE LOGITS
     Playboy
    0.50
     FaceTime
    0.46
     PlayStation
    0.46
    🌃
    0.45
     Kardashian
    0.45
     Shake
    0.44
    🫢
    0.44
     Giải
    0.43
     veya
    0.43
     Shrewsbury
    0.43
    Activations Density 0.001%

    No Known Activations