© 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. 197500
    Prev
    Next
    INDEX
    Explanations

    unlike any, this article, targeted thousands

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

    break down prompts

    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
    ﻠ
    0.60
     Gender
    0.52
     생활
    0.51
    makt
    0.50
    畋
    0.50
     TabLayout
    0.49
     권
    0.49
    잉
    0.48
     아멘
    0.48
    ИС
    0.46
    POSITIVE LOGITS
     tailgate
    0.49
     ছিলো
    0.44
    itrile
    0.44
    coming
    0.43
    粼
    0.42
     chilled
    0.42
    പ്പിച്ച്
    0.42
     attendees
    0.41
    ಡಿಯ
    0.41
    𝐜
    0.41
    Activations Density 0.002%

    No Known Activations