© 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. 42520
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and concepts

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

    legal immigration pathways

    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
    कालिक
    0.48
    ట
    0.48
    蓦
    0.47
    டர்
    0.46
     multiplicar
    0.46
    🤯
    0.45
    पूर्व
    0.45
    🚨
    0.44
    अधिकांश
    0.44
     multiplicación
    0.44
    POSITIVE LOGITS
     Buddhism
    0.47
     وكان
    0.47
     was
    0.45
     είχε
    0.44
     feminism
    0.44
     had
    0.44
     হয়েছিল
    0.42
     buddh
    0.42
     jsem
    0.42
     Islamic
    0.41
    Activations Density 0.000%

    No Known Activations