© 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. 14050
    Prev
    Next
    INDEX
    Explanations

    no matter the occasion

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

    social and organized activities

    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
     quantify
    0.48
     sicherlich
    0.47
    忔
    0.46
     vídeo
    0.44
     episodio
    0.44
     carbono
    0.44
     ලබා
    0.44
     فائد
    0.44
     prilikom
    0.44
     পদ্ধ
    0.43
    POSITIVE LOGITS
    ipitation
    0.42
    領
    0.41
    ceptive
    0.40
    ![
    0.40
    cultures
    0.39
    или
    0.39
    vention
    0.39
     cultures
    0.38
    并且
    0.38
    ষ্ঠ
    0.38
    Activations Density 0.000%

    No Known Activations