© 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. 186270
    Prev
    Next
    INDEX
    Explanations

    common english words

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

    first-person statements and relating to groups

    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
     drifted
    0.44
    居
    0.40
    仅
    0.39
     πριν
    0.39
     tramite
    0.38
     ƙ
    0.38
     gifting
    0.38
     μέσω
    0.37
     अच्छे
    0.37
    ভিং
    0.36
    POSITIVE LOGITS
     عندنا
    0.47
     사람
    0.45
    씹
    0.43
     यानी
    0.42
     naše
    0.42
     من
    0.42
     jūs
    0.42
     unserer
    0.41
     אתה
    0.41
    আমাদের
    0.40
    Activations Density 0.021%

    No Known Activations