© 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. 19996
    Prev
    Next
    INDEX
    Explanations

    units per mass

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

    per capita

    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
    别人的
    0.46
    arrière
    0.43
    蘑
    0.42
    ὧ
    0.42
    𝔱
    0.42
    bgcolor
    0.41
    habilitation
    0.41
    меня
    0.40
    卖家
    0.40
    景
    0.40
    POSITIVE LOGITS
     space
    0.54
     density
    0.53
     densities
    0.48
     volume
    0.47
     convexes
    0.47
     remained
    0.46
     cycled
    0.45
     perfused
    0.45
     mengikuti
    0.45
     substrate
    0.45
    Activations Density 0.004%

    No Known Activations