© 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. 106543
    Prev
    Next
    INDEX
    Explanations

    acknowledgements and thanks

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

    expressing gratitude and thanks

    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
    கார
    0.50
    捍
    0.45
    இது
    0.44
    あなたが
    0.42
    㺫
    0.42
     बहस
    0.41
    瀋
    0.41
    இ
    0.40
    學者
    0.40
    Ր
    0.40
    POSITIVE LOGITS
     credits
    0.51
     Credits
    0.51
     terima
    0.47
     thanks
    0.45
     köszön
    0.44
     créditos
    0.44
     requiere
    0.43
     thanked
    0.41
    thanks
    0.41
    RFQ
    0.40
    Activations Density 0.010%

    No Known Activations