© 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. 151316
    Prev
    Next
    INDEX
    Explanations

    throughout, visiting, time, residence

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

    bumpy carton, hiking, shaped

    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
    வாழ்
    0.52
     hospitales
    0.48
    াস্থ
    0.48
    
    0.48
    कांड
    0.48
    ینس
    0.46
    င်း
    0.45
    회를
    0.45
     órganos
    0.45
    ┆
    0.45
    POSITIVE LOGITS
    mp
    0.53
     --------
    0.49
    rm
    0.48
    mi
    0.47
     
    0.47
     mij
    0.46
    老公
    0.46
    id
    0.45
    co
    0.44
     મંદ
    0.44
    Activations Density 0.001%

    No Known Activations