© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 18626
    Prev
    Next
    INDEX
    Explanations

    things offered or available

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

    describes item features and quality

    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
    この
    0.55
     dieser
    0.50
    important
    0.50
    This
    0.49
     denna
    0.49
     በዚህ
    0.49
    本
    0.48
    這個
    0.48
    今回の
    0.48
     이번
    0.47
    POSITIVE LOGITS
    讓你
    0.58
     harán
    0.56
    让你
    0.55
     boasts
    0.50
     parfaite
    0.50
     તમને
    0.49
     вас
    0.49
    给你
    0.46
     كل
    0.46
     đủ
    0.46
    Activations Density 0.049%

    No Known Activations