© 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. 58148
    Prev
    Next
    INDEX
    Explanations

    separating list items

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

    unix commands

    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
    -
    0.51
    ON
    0.44
    
    0.43
    IBILITY
    0.43
    DAQ
    0.42
    -${
    0.42
    URCH
    0.42
    XX
    0.42
    OKE
    0.42
    -__
    0.42
    POSITIVE LOGITS
    ່າຍ
    0.46
     शास्त्रों
    0.45
     सर्दियों
    0.45
     |.
    0.42
     Fiverr
    0.41
     नए
    0.40
     altın
    0.39
     正規品
    0.39
    𝐠
    0.39
    ▍
    0.38
    Activations Density 0.019%

    No Known Activations