© 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. 185894
    Prev
    Next
    INDEX
    Explanations

    Swedish techniques, Christmas parties, opinion paragraphs

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

    responsible for infrastructure

    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
    이니까
    0.57
    שׁ
    0.52
    וט
    0.48
    丧
    0.45
    たり
    0.45
    这种情况
    0.44
    呕
    0.44
    🥶
    0.43
    🤦
    0.43
    㖵
    0.43
    POSITIVE LOGITS
     améli
    0.54
     améliorer
    0.53
     Compressed
    0.52
     trois
    0.50
    сыпа
    0.50
     compressed
    0.49
     wysok
    0.49
     obtenir
    0.49
     ofer
    0.49
    p
    0.49
    Activations Density 0.000%

    No Known Activations