© 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. 221592
    Prev
    Next
    INDEX
    Explanations

    any other features

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

    conversational acknowledgments

    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
    ﺮ
    0.47
    രെ
    0.46
    空间
    0.46
    考试
    0.45
    διά
    0.45
    ى
    0.45
    दुनिया
    0.45
    ющие
    0.45
    лина
    0.44
     डॉक्यूमेंट्री
    0.44
    POSITIVE LOGITS
     Wam
    0.53
     し
    0.52
     ரி
    0.47
     &=
    0.46
     defensively
    0.46
     monotonically
    0.45
    SelfPermission
    0.45
     سە
    0.45
     डिफेंस
    0.44
     대응
    0.44
    Activations Density 0.000%

    No Known Activations