© 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. 99533
    Prev
    Next
    INDEX
    Explanations

    lung, Lord, carcinogen, drivers, lot

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

    functional components, Canvas, VRAM

    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
    팍
    0.55
    x
    0.51
    𝕚
    0.50
    alak
    0.50
    संयुक्त
    0.49
     представля
    0.47
    ]。
    0.47
     энцикло
    0.46
    हि
    0.46
    b
    0.46
    POSITIVE LOGITS
     లు
    0.46
     سنة
    0.42
     offsetY
    0.41
     Harvesting
    0.41
    眩
    0.39
    రు
    0.39
     calend
    0.39
    enger
    0.39
    হাম্ম
    0.39
     café
    0.38
    Activations Density 0.001%

    No Known Activations